{ "schemaVersion": 2, "description": "All 51 supplied public-data prediction tasks. Scores are recorded evaluation means, not newly executed predictions or customer outcome measurements.", "metrics": { "roc_auc": { "direction": "higher", "change": "Percentage points = 100 * (causilo_mean - strongest_conventional_mean)" }, "rmse": { "direction": "lower", "change": "Relative error change = 100 * (strongest_conventional_mean - causilo_mean) / strongest_conventional_mean" }, "log_loss": { "direction": "lower", "change": "Relative error change = 100 * (strongest_conventional_mean - causilo_mean) / strongest_conventional_mean" } }, "comparison": "Strongest conventional mean across seven model families and all three recorded configurations; Causilo default.", "aggregation": "Calculations use reported means, not per-split percentage changes. Standard deviations are recorded split variability, not confidence intervals.", "sourceSnapshotSha256": "a26005a777202fd163db1cbc0ca45fb4fccaa1891d1c2102998d188fae1ef51a", "recordedSource": { "file": "results_per_split_official.csv", "sha256": "d7bffb24241e79aa98cfdd54d866fc82ef8ee37fba158b32bf9ffd1d091c9fda", "rows": 67728 }, "sourceNote": "Retained provenance from the existing evaluation snapshot. This endpoint publishes aggregate scores, task references and derived changes; it does not redistribute the original records or per-split CSV.", "studies": [ { "slug": "concrete-strength", "dataset": "concrete_compressive_strength", "domain": "science", "sourceUrl": "https://www.openml.org/d/46917", "originalSource": "https://archive.ics.uci.edu/dataset/165/concrete+compressive+strength", "attribution": "I-Cheng Yeh, Concrete Compressive Strength (1998), UCI Machine Learning Repository.", "license": "CC BY 4.0", "licenseUrl": "https://creativecommons.org/licenses/by/4.0/", "rows": 1030, "features": 8, "target": "ConcreteCompressiveStrength", "targetUnit": "MPa", "splits": 30, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 3.912797847114176, "std": 0.45346725924954356 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 4.201709573761268, "std": 0.41793392339138014, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.28891172664709197, "relativeChange": 6.876051796899071, "reductionPercent": 6.876051796899071, "headline": { "value": "6.9%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 3.912797847114176, "std": 0.45346725924954356, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 4.201709573761268, "std": 0.41793392339138014, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 4.211650606985306, "std": 0.3961128777590289, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 4.2221922058184775, "std": 0.3835168178494737, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 5.003252669401765, "std": 0.362715393612672, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 5.106261359494433, "std": 0.3521004682405249, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 6.548413843625973, "std": 0.5546192661941121, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 8.15336989555954, "std": 0.35429418780794836, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 3.912797847114176, "std": 0.45346725924954356 }, { "family": "CAT", "name": "CatBoost", "mean": 4.201709573761268, "std": 0.41793392339138014 }, { "family": "GBM", "name": "LightGBM", "mean": 4.483801100811062, "std": 0.3879164751386327 }, { "family": "XGB", "name": "XGBoost", "mean": 4.7545803196908, "std": 0.38685949900625893 }, { "family": "RF", "name": "Random forest", "mean": 5.261461589652239, "std": 0.3364178705643075 }, { "family": "XT", "name": "Extra trees", "mean": 5.21892802497126, "std": 0.3474820733599713 }, { "family": "LR", "name": "Linear regression", "mean": 8.227584702895252, "std": 0.35858979401949964 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 8.972441171058465, "std": 0.46409136552097524 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 3.912797847114176, "std": 0.45346725924954356 }, { "family": "CAT", "name": "CatBoost", "mean": 4.220941284757924, "std": 0.4145595939277428 }, { "family": "GBM", "name": "LightGBM", "mean": 4.234822235307136, "std": 0.39451316375368833 }, { "family": "XGB", "name": "XGBoost", "mean": 4.235594744424336, "std": 0.3727983083025501 }, { "family": "RF", "name": "Random forest", "mean": 5.188581897050338, "std": 0.3664964813901079 }, { "family": "XT", "name": "Extra trees", "mean": 5.019761933593027, "std": 0.3602916290395284 }, { "family": "LR", "name": "Linear regression", "mean": 8.160319455306995, "std": 0.36151481873041613 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 6.761997852517052, "std": 0.5652773448056292 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 3.912797847114176, "std": 0.45346725924954356 }, { "family": "CAT", "name": "CatBoost", "mean": 4.201835330250513, "std": 0.4144042976089399 }, { "family": "GBM", "name": "LightGBM", "mean": 4.211650606985306, "std": 0.3961128777590289 }, { "family": "XGB", "name": "XGBoost", "mean": 4.2221922058184775, "std": 0.3835168178494737 }, { "family": "RF", "name": "Random forest", "mean": 5.106261359494433, "std": 0.3521004682405249 }, { "family": "XT", "name": "Extra trees", "mean": 5.003252669401765, "std": 0.362715393612672 }, { "family": "LR", "name": "Linear regression", "mean": 8.15336989555954, "std": 0.35429418780794836 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 6.548413843625973, "std": 0.5546192661941121 } ] } }, { "slug": "airfoil-noise", "dataset": "airfoil_self_noise", "domain": "science", "sourceUrl": "https://www.openml.org/d/46904", "originalSource": "https://archive.ics.uci.edu/dataset/291/airfoil+self+noise", "attribution": "Thomas Brooks, D. Stuart Pope and Michael Marcolini, Airfoil Self-Noise (1989), UCI Machine Learning Repository.", "license": "CC BY 4.0", "licenseUrl": "https://creativecommons.org/licenses/by/4.0/", "rows": 1503, "features": 5, "target": "scaled-sound-pressure", "targetUnit": "dB", "splits": 30, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9743497173364202, "std": 0.08322489031975162 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 1.3287170293711439, "std": 0.10237338124972044, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": 0.3543673120347237, "relativeChange": 26.669885626621262, "reductionPercent": 26.669885626621262, "headline": { "value": "26.7%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9743497173364202, "std": 0.08322489031975162, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 1.3287170293711439, "std": 0.10237338124972044, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XGB", "name": "XGBoost", "mean": 1.4391742377013739, "std": 0.10423652038387057, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 1.4511634202955226, "std": 0.10762394673295603, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 1.6530096037906363, "std": 0.09742424611288036, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 1.8513668036936635, "std": 0.09607142437142459, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 2.2212842024517694, "std": 0.12155453855318656, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 4.731823340434003, "std": 0.14399333755827914, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9743497173364202, "std": 0.08322489031975162 }, { "family": "CAT", "name": "CatBoost", "mean": 1.5782966827503813, "std": 0.09086972673218911 }, { "family": "GBM", "name": "LightGBM", "mean": 1.5538343233493532, "std": 0.09345625121433487 }, { "family": "XGB", "name": "XGBoost", "mean": 1.5493776820433396, "std": 0.10411709740095647 }, { "family": "RF", "name": "Random forest", "mean": 1.8984934381282264, "std": 0.09464460169191805 }, { "family": "XT", "name": "Extra trees", "mean": 1.8978868602294279, "std": 0.09095707289861853 }, { "family": "LR", "name": "Linear regression", "mean": 5.34448825013813, "std": 0.1992106747537529 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 3.3691997642485885, "std": 0.11349298221157497 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9743497173364202, "std": 0.08322489031975162 }, { "family": "CAT", "name": "CatBoost", "mean": 1.3287170293711439, "std": 0.10237338124972044 }, { "family": "GBM", "name": "LightGBM", "mean": 1.4802485752082666, "std": 0.10783651298794303 }, { "family": "XGB", "name": "XGBoost", "mean": 1.4391742377013739, "std": 0.10423652038387057 }, { "family": "RF", "name": "Random forest", "mean": 1.89110116919123, "std": 0.10066596982308054 }, { "family": "XT", "name": "Extra trees", "mean": 1.6605701090680889, "std": 0.09516178842760592 }, { "family": "LR", "name": "Linear regression", "mean": 4.752497330166329, "std": 0.1414545401681435 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 2.5987267268401286, "std": 0.15399963625813323 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9743497173364202, "std": 0.08322489031975162 }, { "family": "CAT", "name": "CatBoost", "mean": 1.3299951802896914, "std": 0.10489837563513243 }, { "family": "GBM", "name": "LightGBM", "mean": 1.4511634202955226, "std": 0.10762394673295603 }, { "family": "XGB", "name": "XGBoost", "mean": 1.4426405173789485, "std": 0.10352307729009697 }, { "family": "RF", "name": "Random forest", "mean": 1.8513668036936635, "std": 0.09607142437142459 }, { "family": "XT", "name": "Extra trees", "mean": 1.6530096037906363, "std": 0.09742424611288036 }, { "family": "LR", "name": "Linear regression", "mean": 4.731823340434003, "std": 0.14399333755827914 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 2.2212842024517694, "std": 0.12155453855318656 } ] } }, { "slug": "protein-structure", "dataset": "physiochemical_protein", "domain": "science", "sourceUrl": "https://www.openml.org/d/46949", "originalSource": "https://archive.ics.uci.edu/dataset/265/physicochemical+properties+of+protein+tertiary+structure", "attribution": "Prashant Rana, Physicochemical Properties of Protein Tertiary Structure (2013), UCI Machine Learning Repository.", "license": "CC BY 4.0", "licenseUrl": "https://creativecommons.org/licenses/by/4.0/", "rows": 45730, "features": 9, "target": "ResidualSize", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 2.8470635082949376, "std": 0.03202243529001351 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 3.3814586840724123, "std": 0.027125514598177712, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": 0.5343951757774748, "relativeChange": 15.803687866855242, "reductionPercent": 15.803687866855242, "headline": { "value": "15.8%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 2.8470635082949376, "std": 0.03202243529001351, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 3.3814586840724123, "std": 0.027125514598177712, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "CAT", "name": "CatBoost", "mean": 3.3821160971830944, "std": 0.02756151768447773, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 3.3901219011224066, "std": 0.024122863864296944, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 3.4607261916644925, "std": 0.02068923515714446, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 3.4626717816841124, "std": 0.0211332727520474, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 3.5861526317489316, "std": 0.041316168568209875, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 5.141836088971997, "std": 0.02327453678495104, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 2.8470635082949376, "std": 0.03202243529001351 }, { "family": "CAT", "name": "CatBoost", "mean": 3.521344054243854, "std": 0.02492916986453029 }, { "family": "GBM", "name": "LightGBM", "mean": 3.476865230944445, "std": 0.025925680408126872 }, { "family": "XGB", "name": "XGBoost", "mean": 3.5130282124805694, "std": 0.024111990473075672 }, { "family": "RF", "name": "Random forest", "mean": 3.5650848139846203, "std": 0.02114338202270201 }, { "family": "XT", "name": "Extra trees", "mean": 3.5731200713689937, "std": 0.01993684431367896 }, { "family": "LR", "name": "Linear regression", "mean": 5.193572916810665, "std": 0.02399699028570062 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 3.9094136171054252, "std": 0.03214934080408744 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 2.8470635082949376, "std": 0.03202243529001351 }, { "family": "CAT", "name": "CatBoost", "mean": 3.3951600783756075, "std": 0.028889539641090964 }, { "family": "GBM", "name": "LightGBM", "mean": 3.3814586840724123, "std": 0.027125514598177712 }, { "family": "XGB", "name": "XGBoost", "mean": 3.3901219011224066, "std": 0.024122863864296944 }, { "family": "RF", "name": "Random forest", "mean": 3.4626717816841124, "std": 0.0211332727520474 }, { "family": "XT", "name": "Extra trees", "mean": 3.4672733901361448, "std": 0.021432357558376032 }, { "family": "LR", "name": "Linear regression", "mean": 5.187776722443761, "std": 0.02195238780883999 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 3.6882497482519176, "std": 0.04220074905307206 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 2.8470635082949376, "std": 0.03202243529001351 }, { "family": "CAT", "name": "CatBoost", "mean": 3.3821160971830944, "std": 0.02756151768447773 }, { "family": "GBM", "name": "LightGBM", "mean": 3.3843594917971704, "std": 0.02670574094932677 }, { "family": "XGB", "name": "XGBoost", "mean": 3.3901694802321263, "std": 0.024216554212423504 }, { "family": "RF", "name": "Random forest", "mean": 3.470558879576537, "std": 0.020676042805793115 }, { "family": "XT", "name": "Extra trees", "mean": 3.4607261916644925, "std": 0.02068923515714446 }, { "family": "LR", "name": "Linear regression", "mean": 5.141836088971997, "std": 0.02327453678495104 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 3.5861526317489316, "std": 0.041316168568209875 } ] } }, { "slug": "online-purchase-intent", "dataset": "online_shoppers_intention", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46947", "originalSource": "https://doi.org/10.24432/C5F88Q", "attribution": "Online purchase intent dataset. Original source and curated OpenML task linked below.", "rows": 12330, "features": 17, "target": "Revenue", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9388727311239287, "std": 0.0026394340474769173 }, "strongestConventional": { "family": "XGB", "name": "XGBoost", "mean": 0.9355468113533418, "std": 0.0032770915038266945, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.003325919770586827, "relativeChange": 0.35550543598942136, "reductionPercent": null, "headline": { "value": "0.33 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9388727311239287, "std": 0.0026394340474769173, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9355468113533418, "std": 0.0032770915038266945, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9354608176462708, "std": 0.003434138889430541, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9342823015496569, "std": 0.003839789674613411, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.9316327650305937, "std": 0.0033545072959265225, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.9310791868274135, "std": 0.0038230301798961156, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9219143697797797, "std": 0.00449057659196448, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9175899675215347, "std": 0.006394039933730727, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9388727311239287, "std": 0.0026394340474769173 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9335139402336695, "std": 0.0033296666647449078 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9344258758383632, "std": 0.0030310007232631033 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9351120151010984, "std": 0.003508852316369282 }, { "family": "RF", "name": "Random forest", "mean": 0.9263650470078816, "std": 0.0038167326881429447 }, { "family": "XT", "name": "Extra trees", "mean": 0.9195214817309135, "std": 0.004674801996722442 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9126072608057378, "std": 0.006569629813386523 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7945240464555103, "std": 0.00547155568812697 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9388727311239287, "std": 0.0026394340474769173 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9334436868952027, "std": 0.004193328474450148 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9353999180092748, "std": 0.004374177499946731 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9338724233569771, "std": 0.003424540983317062 }, { "family": "RF", "name": "Random forest", "mean": 0.9306648832275862, "std": 0.003816637095586898 }, { "family": "XT", "name": "Extra trees", "mean": 0.9310791868274135, "std": 0.0038230301798961156 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9125438718772215, "std": 0.006527634320693418 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8972548696576786, "std": 0.007426192167801117 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9388727311239287, "std": 0.0026394340474769173 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9342823015496569, "std": 0.003839789674613411 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9354608176462708, "std": 0.003434138889430541 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9355468113533418, "std": 0.0032770915038266945 }, { "family": "RF", "name": "Random forest", "mean": 0.9316327650305937, "std": 0.0033545072959265225 }, { "family": "XT", "name": "Extra trees", "mean": 0.9306672719416715, "std": 0.0038774989536873696 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9175899675215347, "std": 0.006394039933730727 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9219143697797797, "std": 0.00449057659196448 } ] } }, { "slug": "bank-customer-churn", "dataset": "Bank_Customer_Churn", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46911", "originalSource": "https://www.kaggle.com/datasets/gauravtopre/bank-customer-churn-dataset", "attribution": "Bank customer churn dataset. Original source and curated OpenML task linked below.", "rows": 10000, "features": 10, "target": "churn", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8743744290612709, "std": 0.009179452330555768 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.870227466456198, "std": 0.009314872166205634, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.004146962605072968, "relativeChange": 0.47653777488321797, "reductionPercent": null, "headline": { "value": "0.41 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8743744290612709, "std": 0.009179452330555768, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.870227466456198, "std": 0.009314872166205634, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.8673164916427174, "std": 0.009251222587402621, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8662912173126536, "std": 0.009771002060306873, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.8614420984196223, "std": 0.007249628247279974, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8581408198269685, "std": 0.008043225058160788, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8391567832261863, "std": 0.007185670671334716, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.772748275355099, "std": 0.009665709744268218, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8743744290612709, "std": 0.009179452330555768 }, { "family": "CAT", "name": "CatBoost", "mean": 0.870227466456198, "std": 0.009314872166205634 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8643182288831334, "std": 0.009179241510390882 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8642734363481124, "std": 0.00909611500850005 }, { "family": "RF", "name": "Random forest", "mean": 0.851268153541544, "std": 0.007552889897244658 }, { "family": "XT", "name": "Extra trees", "mean": 0.8541184534310102, "std": 0.006302130280695544 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7721633827679304, "std": 0.009813832326340248 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8136824813068181, "std": 0.00992876933609085 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8743744290612709, "std": 0.009179452330555768 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8698815839774029, "std": 0.008845563873476433 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8664527175963993, "std": 0.009473349086818595 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8662590422850289, "std": 0.010015653078368492 }, { "family": "RF", "name": "Random forest", "mean": 0.8567421417246177, "std": 0.007872576379546647 }, { "family": "XT", "name": "Extra trees", "mean": 0.8605021110889476, "std": 0.007881575556066665 }, { "family": "LR", "name": "Logistic regression", "mean": 0.772748275355099, "std": 0.009665709744268218 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.826590690695661, "std": 0.008852996660511366 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8743744290612709, "std": 0.009179452330555768 }, { "family": "CAT", "name": "CatBoost", "mean": 0.870112583192617, "std": 0.008637775443784159 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8673164916427174, "std": 0.009251222587402621 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8662912173126536, "std": 0.009771002060306873 }, { "family": "RF", "name": "Random forest", "mean": 0.8581408198269685, "std": 0.008043225058160788 }, { "family": "XT", "name": "Extra trees", "mean": 0.8614420984196223, "std": 0.007249628247279974 }, { "family": "LR", "name": "Logistic regression", "mean": 0.77274799845314, "std": 0.009663042554099154 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8391567832261863, "std": 0.007185670671334716 } ] } }, { "slug": "term-deposit-response", "dataset": "bank-marketing", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46910", "originalSource": "https://doi.org/10.24432/C5K306", "attribution": "Term deposit subscriptions dataset. Original source and curated OpenML task linked below.", "rows": 45211, "features": 13, "target": "SubscribeTermDeposit", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7673472858422093, "std": 0.005641505785614934 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.7656098458485188, "std": 0.004837724729619741, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.0017374399936905816, "relativeChange": 0.22693542972465197, "reductionPercent": null, "headline": { "value": "0.17 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7673472858422093, "std": 0.005641505785614934, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7656098458485188, "std": 0.004837724729619741, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7655221672484325, "std": 0.00498388632354699, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7654655710589703, "std": 0.005454063183780708, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.76140227427824, "std": 0.005081042055922285, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.7576742139711354, "std": 0.004829367894089745, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7555142600368796, "std": 0.004773927109196059, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7483134652117848, "std": 0.004265180774248444, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7673472858422093, "std": 0.005641505785614934 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7656098458485188, "std": 0.004837724729619741 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7633248848141844, "std": 0.004813809789388466 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7632540449085446, "std": 0.005284896839050702 }, { "family": "RF", "name": "Random forest", "mean": 0.7264766236404661, "std": 0.005761105210181063 }, { "family": "XT", "name": "Extra trees", "mean": 0.7254838292455664, "std": 0.003582783832766761 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7477858416446264, "std": 0.004021915954195727 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7117417330672895, "std": 0.005437237881157774 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7673472858422093, "std": 0.005641505785614934 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7655435369595303, "std": 0.005073539218694433 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7652880949629616, "std": 0.004930932215222506 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7652266459874115, "std": 0.0055788630545766105 }, { "family": "RF", "name": "Random forest", "mean": 0.76140227427824, "std": 0.005081042055922285 }, { "family": "XT", "name": "Extra trees", "mean": 0.7576412942678058, "std": 0.004981086459420683 }, { "family": "LR", "name": "Logistic regression", "mean": 0.74779302884394, "std": 0.0039852583985402175 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7486327116384194, "std": 0.005573396227575232 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7673472858422093, "std": 0.005641505785614934 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7654907576414494, "std": 0.004956421321405759 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7655221672484325, "std": 0.00498388632354699 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7654655710589703, "std": 0.005454063183780708 }, { "family": "RF", "name": "Random forest", "mean": 0.7613688735769648, "std": 0.00526493782109728 }, { "family": "XT", "name": "Extra trees", "mean": 0.7576742139711354, "std": 0.004829367894089745 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7483134652117848, "std": 0.004265180774248444 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7555142600368796, "std": 0.004773927109196059 } ] } }, { "slug": "telecom-customer-churn", "dataset": "churn", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46915", "originalSource": "https://github.com/EpistasisLab/pmlb/tree/master/datasets/churn", "attribution": "Telecom customer churn dataset. Original source and curated OpenML task linked below.", "rows": 5000, "features": 19, "target": "CustomerChurned", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9369360457219121, "std": 0.00898179362084917 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.9241681436305246, "std": 0.011653322277145255, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.012767902091387562, "relativeChange": 1.3815561788604642, "reductionPercent": null, "headline": { "value": "1.28 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9369360457219121, "std": 0.00898179362084917, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9241681436305246, "std": 0.011653322277145255, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9227412057193999, "std": 0.009471181826542652, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.9222206037851212, "std": 0.00949848995942407, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9204240938019264, "std": 0.011481073826947194, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "RF", "name": "Random forest", "mean": 0.915455620704649, "std": 0.009374613446296424, "configuration": "default", "configurationLabel": "default" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8992550555228928, "std": 0.009593747541887769, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.8254484533803452, "std": 0.007810963317843347, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9369360457219121, "std": 0.00898179362084917 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9241681436305246, "std": 0.011653322277145255 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9164149226956878, "std": 0.01083450153171387 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9227412057193999, "std": 0.009471181826542652 }, { "family": "RF", "name": "Random forest", "mean": 0.915455620704649, "std": 0.009374613446296424 }, { "family": "XT", "name": "Extra trees", "mean": 0.9167545543814046, "std": 0.009166406858240508 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7772756338666308, "std": 0.018038340278762797 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8663355772767735, "std": 0.004441138139182127 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9369360457219121, "std": 0.00898179362084917 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9236966457219066, "std": 0.01232181025023275 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9204240938019264, "std": 0.011481073826947194 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9212484704999377, "std": 0.010864288875215275 }, { "family": "RF", "name": "Random forest", "mean": 0.9129611639217218, "std": 0.0124189428624095 }, { "family": "XT", "name": "Extra trees", "mean": 0.9201368443170191, "std": 0.0081915075202386 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8254484533803452, "std": 0.007810963317843347 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8916237255822852, "std": 0.00954824473952188 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9369360457219121, "std": 0.00898179362084917 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9233731963071521, "std": 0.010155451376030319 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9203817358309122, "std": 0.011176983306221374 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9200167397637423, "std": 0.0108219142318325 }, { "family": "RF", "name": "Random forest", "mean": 0.9127123803186065, "std": 0.011416988831950973 }, { "family": "XT", "name": "Extra trees", "mean": 0.9222206037851212, "std": 0.00949848995942407 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8253570354846814, "std": 0.007970088139479949 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8992550555228928, "std": 0.009593747541887769 } ] } }, { "slug": "airline-passenger-satisfaction", "dataset": "customer_satisfaction_in_airline", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46920", "originalSource": "https://www.kaggle.com/datasets/yakhyojon/customer-satisfaction-in-airline", "attribution": "Airline passenger satisfaction dataset. Original source and curated OpenML task linked below.", "rows": 129880, "features": 21, "target": "satisfaction", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9954371670666345, "std": 0.00018025570735303285 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.9948471147161291, "std": 0.0001854565368021924, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.0005900523505054656, "relativeChange": 0.059310857093236066, "reductionPercent": null, "headline": { "value": "0.06 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9954371670666345, "std": 0.00018025570735303285, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9948471147161291, "std": 0.0001854565368021924, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9946702927681788, "std": 0.00019626693704206496, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9944459438257088, "std": 0.00020235919139070333, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.9939554500970873, "std": 0.0002376108177061957, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.9931130159526775, "std": 0.00031064115710332895, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9883423640788138, "std": 0.00029129629851606915, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9645394988766043, "std": 0.0008268650396363546, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9954371670666345, "std": 0.00018025570735303285 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9947781048852657, "std": 0.0001871954597935564 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9943590276282381, "std": 0.00019582408301430386 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9941966846628109, "std": 0.00021562286603370154 }, { "family": "RF", "name": "Random forest", "mean": 0.9925215719386259, "std": 0.00031702578230654313 }, { "family": "XT", "name": "Extra trees", "mean": 0.9919789940896896, "std": 0.0002936218809558784 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9643882819218615, "std": 0.0008104481482049898 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9845836024639304, "std": 0.00045935690499285313 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9954371670666345, "std": 0.00018025570735303285 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9947592849070368, "std": 0.0001969706860313416 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9945039265682659, "std": 0.00020483454616201317 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9944165657704758, "std": 0.00020900284064996337 }, { "family": "RF", "name": "Random forest", "mean": 0.9930082442457098, "std": 0.00033388138126385004 }, { "family": "XT", "name": "Extra trees", "mean": 0.9938747400471781, "std": 0.0002567782720814321 }, { "family": "LR", "name": "Logistic regression", "mean": 0.964477775856894, "std": 0.0008216804299577777 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9847115009019081, "std": 0.00046597487033082447 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9954371670666345, "std": 0.00018025570735303285 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9948471147161291, "std": 0.0001854565368021924 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9946702927681788, "std": 0.00019626693704206496 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9944459438257088, "std": 0.00020235919139070333 }, { "family": "RF", "name": "Random forest", "mean": 0.9931130159526775, "std": 0.00031064115710332895 }, { "family": "XT", "name": "Extra trees", "mean": 0.9939554500970873, "std": 0.0002376108177061957 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9645394988766043, "std": 0.0008268650396363546 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9883423640788138, "std": 0.00029129629851606915 } ] } }, { "slug": "fitness-class-attendance", "dataset": "Fitness_Club", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46927", "originalSource": "https://www.kaggle.com/datasets/ddosad/datacamps-data-science-associate-certification", "attribution": "Fitness class attendance dataset. Original source and curated OpenML task linked below.", "rows": 1500, "features": 6, "target": "attended", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.820580561683625, "std": 0.01278729683147126 }, "strongestConventional": { "family": "LR", "name": "Logistic regression", "mean": 0.8188863561586994, "std": 0.014477402502646685, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.0016942055249256072, "relativeChange": 0.20689140955686794, "reductionPercent": null, "headline": { "value": "0.17 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.820580561683625, "std": 0.01278729683147126, "configuration": "default", "configurationLabel": "default" }, { "family": "LR", "name": "Logistic regression", "mean": 0.8188863561586994, "std": 0.014477402502646685, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.8164309415890639, "std": 0.013011153183360226, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 0.814802907279415, "std": 0.015022085012746064, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "CAT", "name": "CatBoost", "mean": 0.8135582448493155, "std": 0.014229303029680404, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8083577566387936, "std": 0.014587300082438763, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8010932076410023, "std": 0.015253836902809553, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7984497009952856, "std": 0.01560893698723065, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.820580561683625, "std": 0.01278729683147126 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8135582448493155, "std": 0.014229303029680404 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7947769451812592, "std": 0.015357314146373426 }, { "family": "XGB", "name": "XGBoost", "mean": 0.798092637081898, "std": 0.01468625260031258 }, { "family": "RF", "name": "Random forest", "mean": 0.7754996299871569, "std": 0.017927722647372163 }, { "family": "XT", "name": "Extra trees", "mean": 0.7749823397504138, "std": 0.017602717237657134 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8188863561586994, "std": 0.014477402502646685 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7222323611858382, "std": 0.02631750147778321 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.820580561683625, "std": 0.01278729683147126 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8120252338937729, "std": 0.013686308402350834 }, { "family": "GBM", "name": "LightGBM", "mean": 0.814802907279415, "std": 0.015022085012746064 }, { "family": "XGB", "name": "XGBoost", "mean": 0.808192053841816, "std": 0.015030911585328014 }, { "family": "RF", "name": "Random forest", "mean": 0.8010932076410023, "std": 0.015253836902809553 }, { "family": "XT", "name": "Extra trees", "mean": 0.8164309415890639, "std": 0.013011153183360226 }, { "family": "LR", "name": "Logistic regression", "mean": 0.818574213054246, "std": 0.014671892054660298 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7863069301424109, "std": 0.01628279791200988 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.820580561683625, "std": 0.01278729683147126 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8109065337410536, "std": 0.014824997385386878 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8144249576027305, "std": 0.014624477309095295 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8083577566387936, "std": 0.014587300082438763 }, { "family": "RF", "name": "Random forest", "mean": 0.7998810525034481, "std": 0.015300687484186738 }, { "family": "XT", "name": "Extra trees", "mean": 0.8136597094433333, "std": 0.01363119954762332 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8186761352696659, "std": 0.01459483549528548 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7984497009952856, "std": 0.01560893698723065 } ] } }, { "slug": "coupon-acceptance", "dataset": "in_vehicle_coupon_recommendation", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46937", "originalSource": "https://doi.org/10.24432/C5GS4P", "attribution": "Coupon acceptance dataset. Original source and curated OpenML task linked below.", "rows": 12684, "features": 24, "target": "AcceptCoupon", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8440871553080485, "std": 0.005641562863299644 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.8448694896123582, "std": 0.0052861509590563975, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": -0.0007823343043097397, "relativeChange": -0.09259824315216889, "reductionPercent": null, "headline": { "value": "0.08 pp", "label": "lower ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8440871553080485, "std": 0.005641562863299644, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.8448694896123582, "std": 0.0052861509590563975, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.8444515810647816, "std": 0.0056876959099089125, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8425401461690539, "std": 0.00507180750578826, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8220046249062807, "std": 0.007705597080348697, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.8109225165892049, "std": 0.007639736176904129, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8066745329639227, "std": 0.00636696222738438, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7354973606917672, "std": 0.007091754668939807, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8440871553080485, "std": 0.005641562863299644 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8390278330499753, "std": 0.005620940862016107 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8358038040840271, "std": 0.0052402497504244585 }, { "family": "XGB", "name": "XGBoost", "mean": 0.832429739118053, "std": 0.004461778311612152 }, { "family": "RF", "name": "Random forest", "mean": 0.8124784358157243, "std": 0.007175170652706959 }, { "family": "XT", "name": "Extra trees", "mean": 0.7992245911438071, "std": 0.0071744682742793135 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7351089837028664, "std": 0.006837004043386063 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7278548688095685, "std": 0.009043501210665853 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8440871553080485, "std": 0.005641562863299644 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8429755910862253, "std": 0.005842347582793346 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8440650390002764, "std": 0.005438167141768418 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8421383421841101, "std": 0.004980745737622891 }, { "family": "RF", "name": "Random forest", "mean": 0.8172849642510108, "std": 0.007558877325287231 }, { "family": "XT", "name": "Extra trees", "mean": 0.8041535296817686, "std": 0.007439226625033872 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7353204666216815, "std": 0.007348800908533866 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7783010084037691, "std": 0.006757408641938638 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8440871553080485, "std": 0.005641562863299644 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8444515810647816, "std": 0.0056876959099089125 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8448694896123582, "std": 0.0052861509590563975 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8425401461690539, "std": 0.00507180750578826 }, { "family": "RF", "name": "Random forest", "mean": 0.8220046249062807, "std": 0.007705597080348697 }, { "family": "XT", "name": "Extra trees", "mean": 0.8109225165892049, "std": 0.007639736176904129 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7354973606917672, "std": 0.007091754668939807 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8066745329639227, "std": 0.00636696222738438 } ] } }, { "slug": "customer-offer-response", "dataset": "kddcup09_appetency", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46939", "originalSource": "https://kdd.org/kdd-cup/view/kdd-cup-2009/Intro", "attribution": "Customer offer response dataset. Original source and curated OpenML task linked below.", "rows": 50000, "features": 212, "target": "appetency", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.832847693810753, "std": 0.008824064356010526 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.8456914928942011, "std": 0.009257859794862391, "configuration": "default", "configurationLabel": "default" }, "signedDifference": -0.012843799083448126, "relativeChange": -1.5187333905290838, "reductionPercent": null, "headline": { "value": "1.28 pp", "label": "lower ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.832847693810753, "std": 0.008824064356010526, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.8456914928942011, "std": 0.009257859794862391, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8369511058249774, "std": 0.010267492647087977, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.828630779944158, "std": 0.009663379891473877, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8222277090264771, "std": 0.01108139176712978, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.8218713539625777, "std": 0.009993330849068408, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.8209747121089855, "std": 0.01371835577393227, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7762219415845629, "std": 0.013376954831408425, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.832847693810753, "std": 0.008824064356010526 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8456914928942011, "std": 0.009257859794862391 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7975660280227409, "std": 0.009287062420993282 }, { "family": "XGB", "name": "XGBoost", "mean": 0.829629991038903, "std": 0.011668883983687456 }, { "family": "RF", "name": "Random forest", "mean": 0.7724925897124363, "std": 0.016452229430581215 }, { "family": "XT", "name": "Extra trees", "mean": 0.7906883471279725, "std": 0.015321173905005045 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7968027858757852, "std": 0.013399962983447021 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6052769675292243, "std": 0.010289051907318924 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.832847693810753, "std": 0.008824064356010526 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8448822561477826, "std": 0.008418658424610617 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8210211652450164, "std": 0.008725141782459887 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8330030381093471, "std": 0.009354236646712394 }, { "family": "RF", "name": "Random forest", "mean": 0.8222277090264771, "std": 0.01108139176712978 }, { "family": "XT", "name": "Extra trees", "mean": 0.8203946598375771, "std": 0.009857435746659766 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8197852538524839, "std": 0.014132331918905358 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7598992479503068, "std": 0.011843283003336978 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.832847693810753, "std": 0.008824064356010526 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8446362334054929, "std": 0.008327341723758985 }, { "family": "GBM", "name": "LightGBM", "mean": 0.828630779944158, "std": 0.009663379891473877 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8369511058249774, "std": 0.010267492647087977 }, { "family": "RF", "name": "Random forest", "mean": 0.8213695343298106, "std": 0.010395365027763198 }, { "family": "XT", "name": "Extra trees", "mean": 0.8218713539625777, "std": 0.009993330849068408 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8209747121089855, "std": 0.01371835577393227 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7762219415845629, "std": 0.013376954831408425 } ] } }, { "slug": "marketing-campaign-response", "dataset": "Marketing_Campaign", "domain": "customers", "sourceUrl": "https://www.openml.org/d/46940", "originalSource": "https://www.kaggle.com/datasets/rodsaldanha/arketing-campaign", "attribution": "Marketing campaign response dataset. Original source and curated OpenML task linked below.", "rows": 2240, "features": 25, "target": "Response", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.923754011017512, "std": 0.012278728004062734 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.9110357339320346, "std": 0.014109155571996409, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.012718277085477347, "relativeChange": 1.3960239551290927, "reductionPercent": null, "headline": { "value": "1.27 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.923754011017512, "std": 0.012278728004062734, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9110357339320346, "std": 0.014109155571996409, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9065856267902769, "std": 0.0144998810826038, "configuration": "default", "configurationLabel": "default" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9056604250269753, "std": 0.012938679151760987, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9041022438912797, "std": 0.01515459429179706, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.8883050393656173, "std": 0.014443280919181305, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8826444336233, "std": 0.015147392284089832, "configuration": "default", "configurationLabel": "default" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8754764579773865, "std": 0.014320399784399316, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.923754011017512, "std": 0.012278728004062734 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9065856267902769, "std": 0.0144998810826038 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9013052265022626, "std": 0.014300895768843906 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8974691732423682, "std": 0.015469662194415857 }, { "family": "RF", "name": "Random forest", "mean": 0.8826444336233, "std": 0.015147392284089832 }, { "family": "XT", "name": "Extra trees", "mean": 0.8872709931767836, "std": 0.015092632026813713 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9056604250269753, "std": 0.012938679151760987 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8337333545103565, "std": 0.018059654606506884 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.923754011017512, "std": 0.012278728004062734 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9022665470615255, "std": 0.013944044130296339 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9106621959045448, "std": 0.014638283673930863 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9031539766627421, "std": 0.015505824895968268 }, { "family": "RF", "name": "Random forest", "mean": 0.8812926217996973, "std": 0.015573739231200943 }, { "family": "XT", "name": "Extra trees", "mean": 0.8864717240214938, "std": 0.013757984659385561 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9052205380056925, "std": 0.013087931596323488 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8544872513811007, "std": 0.017884232980835753 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.923754011017512, "std": 0.012278728004062734 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9028005857004149, "std": 0.0139490976542758 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9110357339320346, "std": 0.014109155571996409 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9041022438912797, "std": 0.01515459429179706 }, { "family": "RF", "name": "Random forest", "mean": 0.8819891857921125, "std": 0.01477913693504434 }, { "family": "XT", "name": "Extra trees", "mean": 0.8883050393656173, "std": 0.014443280919181305 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9048367854451645, "std": 0.01295763533064369 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8754764579773865, "std": 0.014320399784399316 } ] } }, { "slug": "future-financial-distress", "dataset": "GiveMeSomeCredit", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46929", "originalSource": "https://www.kaggle.com/competitions/GiveMeSomeCredit", "attribution": "Future financial distress dataset. Original source and curated OpenML task linked below.", "rows": 150000, "features": 10, "target": "FinancialDistressNextTwoYears", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8680398579108608, "std": 0.0022375546523027492 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.86658601434547, "std": 0.002235262921704425, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": 0.0014538435653908, "relativeChange": 0.16776679306195402, "reductionPercent": null, "headline": { "value": "0.15 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8680398579108608, "std": 0.0022375546523027492, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.86658601434547, "std": 0.002235262921704425, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 0.8665521396836541, "std": 0.0022520212780893292, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8664334903654317, "std": 0.0021228189450827823, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8629272405469756, "std": 0.002639468982304666, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8589863915509703, "std": 0.0023760711854899814, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.8566037224872212, "std": 0.0028581659531309606, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.8413903178610603, "std": 0.00224677138522681, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8680398579108608, "std": 0.0022375546523027492 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8663547237069028, "std": 0.002326471632227847 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8654346634794798, "std": 0.0022577671809136 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8649903844528922, "std": 0.0019962774927229886 }, { "family": "RF", "name": "Random forest", "mean": 0.8463542555369727, "std": 0.002937518069551447 }, { "family": "XT", "name": "Extra trees", "mean": 0.8448191702160207, "std": 0.0030470906819909213 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8407466255360051, "std": 0.00208259156847104 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7471702486761163, "std": 0.004030001152333068 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8680398579108608, "std": 0.0022375546523027492 }, { "family": "CAT", "name": "CatBoost", "mean": 0.86658601434547, "std": 0.002235262921704425 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8663739494426241, "std": 0.0023434216780577888 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8662956527211882, "std": 0.0021735457230631886 }, { "family": "RF", "name": "Random forest", "mean": 0.8620627504698793, "std": 0.003095039572296033 }, { "family": "XT", "name": "Extra trees", "mean": 0.8566037224872212, "std": 0.0028581659531309606 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8409196845912773, "std": 0.0020628924703377104 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8580617783848724, "std": 0.0023045452680554948 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8680398579108608, "std": 0.0022375546523027492 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8665152850719924, "std": 0.0022846212840703047 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8665521396836541, "std": 0.0022520212780893292 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8664334903654317, "std": 0.0021228189450827823 }, { "family": "RF", "name": "Random forest", "mean": 0.8629272405469756, "std": 0.002639468982304666 }, { "family": "XT", "name": "Extra trees", "mean": 0.8564705254272366, "std": 0.00265787135903924 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8413903178610603, "std": 0.00224677138522681 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8589863915509703, "std": 0.0023760711854899814 } ] } }, { "slug": "credit-application-risk", "dataset": "credit-g", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46918", "originalSource": "https://doi.org/10.24432/C5NC77", "attribution": "German credit risk dataset. Original source and curated OpenML task linked below.", "rows": 1000, "features": 20, "target": "good_or_bad_customer", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8026185393052346, "std": 0.020610435269587966 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.7963216744311165, "std": 0.019951663603498326, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.00629686487411818, "relativeChange": 0.790743876036853, "reductionPercent": null, "headline": { "value": "0.63 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8026185393052346, "std": 0.020610435269587966, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7963216744311165, "std": 0.019951663603498326, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7947030495335217, "std": 0.01802729758660107, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.79346200310578, "std": 0.020820346298653942, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7867299805583068, "std": 0.020858891802853434, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7838507391511683, "std": 0.02205649415965328, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.7831457913013707, "std": 0.01717891186711748, "configuration": "default", "configurationLabel": "default" }, { "family": "RF", "name": "Random forest", "mean": 0.7830742269175746, "std": 0.016978867674879824, "configuration": "default", "configurationLabel": "default" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8026185393052346, "std": 0.020610435269587966 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7887219471039213, "std": 0.016829510622374963 }, { "family": "GBM", "name": "LightGBM", "mean": 0.771415226880892, "std": 0.01910464232402989 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7833288519618992, "std": 0.021432014633691227 }, { "family": "RF", "name": "Random forest", "mean": 0.7830742269175746, "std": 0.016978867674879824 }, { "family": "XT", "name": "Extra trees", "mean": 0.7831457913013707, "std": 0.01717891186711748 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7806514128853185, "std": 0.021422137866852473 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7561818073438245, "std": 0.03127555466404588 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8026185393052346, "std": 0.020610435269587966 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7945483657972928, "std": 0.019699138074451006 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7923290476015799, "std": 0.01984534169198706 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7918507758336084, "std": 0.02055606345247901 }, { "family": "RF", "name": "Random forest", "mean": 0.7811805570839906, "std": 0.018692870340187545 }, { "family": "XT", "name": "Extra trees", "mean": 0.7813080897007936, "std": 0.017483588061112793 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7867299805583068, "std": 0.020858891802853434 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7778230316814008, "std": 0.022441317516722372 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8026185393052346, "std": 0.020610435269587966 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7947030495335217, "std": 0.01802729758660107 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7963216744311165, "std": 0.019951663603498326 }, { "family": "XGB", "name": "XGBoost", "mean": 0.79346200310578, "std": 0.020820346298653942 }, { "family": "RF", "name": "Random forest", "mean": 0.7822370602692491, "std": 0.019330781334446302 }, { "family": "XT", "name": "Extra trees", "mean": 0.7819684775564604, "std": 0.01707758235870227 }, { "family": "LR", "name": "Logistic regression", "mean": 0.786530690974897, "std": 0.020605648728912327 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7838507391511683, "std": 0.02205649415965328 } ] } }, { "slug": "credit-card-payment-default", "dataset": "credit_card_clients_default", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46919", "originalSource": "https://doi.org/10.24432/C55S3H", "attribution": "Credit card payment default dataset. Original source and curated OpenML task linked below.", "rows": 30000, "features": 23, "target": "DefaultOnPaymentNextMonth", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.79151202942369, "std": 0.003674397929870535 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.7854579415336227, "std": 0.003975704079302573, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.006054087890067339, "relativeChange": 0.770771746001652, "reductionPercent": null, "headline": { "value": "0.61 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.79151202942369, "std": 0.003674397929870535, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7854579415336227, "std": 0.003975704079302573, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7852258518357531, "std": 0.004132487449971806, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7847004186644285, "std": 0.0036485422825389404, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.7820256661639948, "std": 0.003920293865757211, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.780343031978947, "std": 0.003974398570993578, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7691145351049342, "std": 0.004098632153544214, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7453928930811574, "std": 0.003847124726036161, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.79151202942369, "std": 0.003674397929870535 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7846731972724249, "std": 0.003615323375050136 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7838930904193186, "std": 0.0038369393717947848 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7829901245007982, "std": 0.0037480367748951525 }, { "family": "RF", "name": "Random forest", "mean": 0.7654291791547745, "std": 0.005099115624706476 }, { "family": "XT", "name": "Extra trees", "mean": 0.7700229059580593, "std": 0.003775140797464755 }, { "family": "LR", "name": "Logistic regression", "mean": 0.745378893784547, "std": 0.0038643921308509407 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7358872803855103, "std": 0.004101159131625411 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.79151202942369, "std": 0.003674397929870535 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7847004186644285, "std": 0.0036485422825389404 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7849992896187382, "std": 0.0037451972429827602 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7850080774748228, "std": 0.004263871349660047 }, { "family": "RF", "name": "Random forest", "mean": 0.7798359678455151, "std": 0.004106722563714794 }, { "family": "XT", "name": "Extra trees", "mean": 0.7801405662245611, "std": 0.0046075395839611545 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7453014219802463, "std": 0.003943582911244305 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7575714587823041, "std": 0.004040668709576233 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.79151202942369, "std": 0.003674397929870535 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7846620423387748, "std": 0.003585488110240609 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7854579415336227, "std": 0.003975704079302573 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7852258518357531, "std": 0.004132487449971806 }, { "family": "RF", "name": "Random forest", "mean": 0.780343031978947, "std": 0.003974398570993578 }, { "family": "XT", "name": "Extra trees", "mean": 0.7820256661639948, "std": 0.003920293865757211 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7453928930811574, "std": 0.003847124726036161 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7691145351049342, "std": 0.004098632153544214 } ] } }, { "slug": "home-equity-credit-performance", "dataset": "heloc", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46932", "originalSource": "https://www.kaggle.com/datasets/averkiyoliabev/home-equity-line-of-creditheloc", "attribution": "Home equity credit performance dataset. Original source and curated OpenML task linked below.", "rows": 10459, "features": 23, "target": "RiskPerformance", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8024850355232537, "std": 0.0037325857101867576 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.7987189593721477, "std": 0.004842723185202664, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.0037660761511060237, "relativeChange": 0.4715145555160527, "reductionPercent": null, "headline": { "value": "0.38 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8024850355232537, "std": 0.0037325857101867576, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7987189593721477, "std": 0.004842723185202664, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.798484023481097, "std": 0.004331943898693127, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7974982332197387, "std": 0.004516214718114241, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.7934344124410453, "std": 0.005013317881328057, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7932890786634744, "std": 0.005243935383710655, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7881852579238029, "std": 0.004026241372900749, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7864567001012722, "std": 0.004993595117407595, "configuration": "default", "configurationLabel": "default" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8024850355232537, "std": 0.0037325857101867576 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7983075242898666, "std": 0.0042336486144971385 }, { "family": "GBM", "name": "LightGBM", "mean": 0.794414246754139, "std": 0.004821227101429109 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7935151269286972, "std": 0.005290232290916921 }, { "family": "RF", "name": "Random forest", "mean": 0.7907234496917807, "std": 0.005295207294503466 }, { "family": "XT", "name": "Extra trees", "mean": 0.79229977571347, "std": 0.004920596788516232 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7864567001012722, "std": 0.004993595117407595 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7427514715970498, "std": 0.0035345457469917923 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8024850355232537, "std": 0.0037325857101867576 }, { "family": "CAT", "name": "CatBoost", "mean": 0.798484023481097, "std": 0.004331943898693127 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7985673733799898, "std": 0.004817957945938139 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7974982332197387, "std": 0.004516214718114241 }, { "family": "RF", "name": "Random forest", "mean": 0.7924868100905306, "std": 0.0055117405082662175 }, { "family": "XT", "name": "Extra trees", "mean": 0.7931218902960244, "std": 0.004879712705202599 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7863431783029998, "std": 0.005113484215591862 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7881759697917352, "std": 0.0047781643145822575 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8024850355232537, "std": 0.0037325857101867576 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7982916542500518, "std": 0.00435741821407896 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7987189593721477, "std": 0.004842723185202664 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7974541520739072, "std": 0.0045000980441947174 }, { "family": "RF", "name": "Random forest", "mean": 0.7932890786634744, "std": 0.005243935383710655 }, { "family": "XT", "name": "Extra trees", "mean": 0.7934344124410453, "std": 0.005013317881328057 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7863896930020815, "std": 0.005263672277512618 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7881852579238029, "std": 0.004026241372900749 } ] } }, { "slug": "polish-company-bankruptcy", "dataset": "polish_companies_bankruptcy", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46950", "originalSource": "https://doi.org/10.24432/C5F600", "attribution": "Polish company bankruptcy dataset. Original source and curated OpenML task linked below.", "rows": 5910, "features": 64, "target": "company_bankrupt", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9884740244338686, "std": 0.0025407881677737528 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.961036287791427, "std": 0.0077792812497772396, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.027437736642441535, "relativeChange": 2.8550156732891576, "reductionPercent": null, "headline": { "value": "2.74 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9884740244338686, "std": 0.0025407881677737528, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.961036287791427, "std": 0.0077792812497772396, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9578267232773979, "std": 0.007380483562442185, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9565283634731284, "std": 0.007375919411780649, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.9376708175531402, "std": 0.006580800583873939, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.8964955949178824, "std": 0.009766964212380404, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.8935795692089585, "std": 0.012112423383829675, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8518558405452635, "std": 0.0107320644550435, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9884740244338686, "std": 0.0025407881677737528 }, { "family": "CAT", "name": "CatBoost", "mean": 0.961036287791427, "std": 0.0077792812497772396 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9543574962215453, "std": 0.007093662043496784 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9578267232773979, "std": 0.007380483562442185 }, { "family": "RF", "name": "Random forest", "mean": 0.9274045299346239, "std": 0.006705502371445532 }, { "family": "XT", "name": "Extra trees", "mean": 0.8783589064523644, "std": 0.011052657643570484 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8674998229557186, "std": 0.016426602775108455 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7754658811922606, "std": 0.02870669208129807 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9884740244338686, "std": 0.0025407881677737528 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9604319091746717, "std": 0.007862888036005378 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9554429775088161, "std": 0.007824831610624215 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9570272102288545, "std": 0.007386711186486235 }, { "family": "RF", "name": "Random forest", "mean": 0.9345452163110587, "std": 0.008151251837665692 }, { "family": "XT", "name": "Extra trees", "mean": 0.8921413620617813, "std": 0.013818595108400552 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8873160412678446, "std": 0.011303028693563397 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8395922801322312, "std": 0.008113133964206796 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9884740244338686, "std": 0.0025407881677737528 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9605135055916885, "std": 0.007656963054926194 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9565283634731284, "std": 0.007375919411780649 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9568414176651951, "std": 0.008025911536121432 }, { "family": "RF", "name": "Random forest", "mean": 0.9376708175531402, "std": 0.006580800583873939 }, { "family": "XT", "name": "Extra trees", "mean": 0.8935795692089585, "std": 0.012112423383829675 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8964955949178824, "std": 0.009766964212380404 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8518558405452635, "std": 0.0107320644550435 } ] } }, { "slug": "taiwanese-company-bankruptcy", "dataset": "taiwanese_bankruptcy_prediction", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46962", "originalSource": "https://doi.org/10.24432/C5004D", "attribution": "Taiwanese company bankruptcy dataset. Original source and curated OpenML task linked below.", "rows": 6819, "features": 94, "target": "Bankrupt", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9506463404207709, "std": 0.005394421791094944 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.9442186317933856, "std": 0.007027744849363001, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.006427708627385287, "relativeChange": 0.680743676406483, "reductionPercent": null, "headline": { "value": "0.64 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9506463404207709, "std": 0.005394421791094944, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9442186317933856, "std": 0.007027744849363001, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9439875748643433, "std": 0.0059422357384906685, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9435982546080848, "std": 0.007977267041018843, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.9400464917669032, "std": 0.006911459447542001, "configuration": "default", "configurationLabel": "default" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9383418798063063, "std": 0.003499895513866755, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9362257460348903, "std": 0.0070096687187736475, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.9325499088323099, "std": 0.010962020340449895, "configuration": "default", "configurationLabel": "default" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9506463404207709, "std": 0.005394421791094944 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9439875748643433, "std": 0.0059422357384906685 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9382780764111007, "std": 0.008365592256525816 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9409412358591935, "std": 0.007733853970125272 }, { "family": "RF", "name": "Random forest", "mean": 0.9325499088323099, "std": 0.010962020340449895 }, { "family": "XT", "name": "Extra trees", "mean": 0.9400464917669032, "std": 0.006911459447542001 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9359168366309221, "std": 0.004584372847749845 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8697916695737156, "std": 0.017386735322027922 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9506463404207709, "std": 0.005394421791094944 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9429248123537869, "std": 0.006956801872392838 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9434393806369081, "std": 0.0077192025397072265 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9431357730311645, "std": 0.007702465955799081 }, { "family": "RF", "name": "Random forest", "mean": 0.9323665685804765, "std": 0.010704682799159714 }, { "family": "XT", "name": "Extra trees", "mean": 0.9365028453127652, "std": 0.007958626053904582 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9383418798063063, "std": 0.003499895513866755 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.925235272925895, "std": 0.01356400163494461 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9506463404207709, "std": 0.005394421791094944 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9434374087457681, "std": 0.0061584086430382535 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9442186317933856, "std": 0.007027744849363001 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9435982546080848, "std": 0.007977267041018843 }, { "family": "RF", "name": "Random forest", "mean": 0.9324388944737391, "std": 0.012195011092764848 }, { "family": "XT", "name": "Extra trees", "mean": 0.9380757140637721, "std": 0.007440301835588383 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9378806333818575, "std": 0.003427100864550943 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9362257460348903, "std": 0.0070096687187736475 } ] } }, { "slug": "loan-customer-outcomes", "dataset": "Is-this-a-good-customer", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46938", "originalSource": "https://www.kaggle.com/datasets/podsyp/is-this-a-good-customer", "attribution": "Loan customer outcomes dataset. Original source and curated OpenML task linked below.", "rows": 1723, "features": 13, "target": "bad_client_target", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7545226788055864, "std": 0.019559298175083097 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.7489211901392648, "std": 0.018099653170888835, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.005601488666321597, "relativeChange": 0.747941003682908, "reductionPercent": null, "headline": { "value": "0.56 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7545226788055864, "std": 0.019559298175083097, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7489211901392648, "std": 0.018099653170888835, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7463939683978976, "std": 0.02021565044901142, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7437075759865543, "std": 0.0224525795172194, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.740633476979253, "std": 0.023982853780763955, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7384685604724898, "std": 0.02065249159877227, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7289173280332416, "std": 0.02003753996314192, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.7188176231103539, "std": 0.02423829220575057, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7545226788055864, "std": 0.019559298175083097 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7489211901392648, "std": 0.018099653170888835 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7242458894521763, "std": 0.019899961757810135 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7233081151548735, "std": 0.020840471781254043 }, { "family": "RF", "name": "Random forest", "mean": 0.7207319225197418, "std": 0.020240176486228997 }, { "family": "XT", "name": "Extra trees", "mean": 0.7009994458717446, "std": 0.019045900342265668 }, { "family": "LR", "name": "Logistic regression", "mean": 0.737517795454927, "std": 0.021205419596577433 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6517326812022294, "std": 0.037360503466541024 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7545226788055864, "std": 0.019559298175083097 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7438308428092318, "std": 0.020289483707403095 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7407652007455544, "std": 0.021581814732002543 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7415216850383844, "std": 0.023253143778628287 }, { "family": "RF", "name": "Random forest", "mean": 0.7270766910452569, "std": 0.018284362126973226 }, { "family": "XT", "name": "Extra trees", "mean": 0.7127211208350698, "std": 0.025085770837874007 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7352595167329942, "std": 0.020147405387148553 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.740633476979253, "std": 0.023982853780763955 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7545226788055864, "std": 0.019559298175083097 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7450652970692263, "std": 0.020259032720158394 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7463939683978976, "std": 0.02021565044901142 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7437075759865543, "std": 0.0224525795172194 }, { "family": "RF", "name": "Random forest", "mean": 0.7289173280332416, "std": 0.02003753996314192 }, { "family": "XT", "name": "Extra trees", "mean": 0.7188176231103539, "std": 0.02423829220575057 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7384685604724898, "std": 0.02065249159877227 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.729998152905815, "std": 0.022667465543152163 } ] } }, { "slug": "insurance-policy-ownership", "dataset": "coil2000_insurance_policies", "domain": "finance", "sourceUrl": "https://www.openml.org/d/46916", "originalSource": "https://doi.org/10.24432/C5630S", "attribution": "Insurance policy ownership dataset. Original source and curated OpenML task linked below.", "rows": 9822, "features": 85, "target": "MobileHomePolicy", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7775824207023694, "std": 0.009395366534142946 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.76110775918655, "std": 0.014509834186474597, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.016474661515819333, "relativeChange": 2.1645636004850317, "reductionPercent": null, "headline": { "value": "1.65 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7775824207023694, "std": 0.009395366534142946, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.76110775918655, "std": 0.014509834186474597, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7598385201670744, "std": 0.012736150311296506, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7583115366737876, "std": 0.014250382400774373, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.7477034655578906, "std": 0.018104055404219846, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7415719012662987, "std": 0.016498530664492174, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7398516857843707, "std": 0.011985126504634338, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7322166213591226, "std": 0.01436502555464267, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7775824207023694, "std": 0.009395366534142946 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7580277168025374, "std": 0.013140248328813608 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7515049650597655, "std": 0.014006082915840636 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7567326117259884, "std": 0.014572267689619786 }, { "family": "RF", "name": "Random forest", "mean": 0.6969923916269021, "std": 0.013522749430162068 }, { "family": "XT", "name": "Extra trees", "mean": 0.7036035040688355, "std": 0.01683306228263704 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7368236110251769, "std": 0.012094657635389838 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6568403286507052, "std": 0.01987891970324895 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7775824207023694, "std": 0.009395366534142946 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7577059052959818, "std": 0.012137795038853188 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7592179271667318, "std": 0.014708226572513711 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7567369476574767, "std": 0.01610845347530418 }, { "family": "RF", "name": "Random forest", "mean": 0.7405936586491453, "std": 0.017302145522186774 }, { "family": "XT", "name": "Extra trees", "mean": 0.7442050944383469, "std": 0.018336546953566506 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7385482112509356, "std": 0.010657166501030126 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7181130527789449, "std": 0.014985215219315314 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7775824207023694, "std": 0.009395366534142946 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7598385201670744, "std": 0.012736150311296506 }, { "family": "GBM", "name": "LightGBM", "mean": 0.76110775918655, "std": 0.014509834186474597 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7583115366737876, "std": 0.014250382400774373 }, { "family": "RF", "name": "Random forest", "mean": 0.7415719012662987, "std": 0.016498530664492174 }, { "family": "XT", "name": "Extra trees", "mean": 0.7477034655578906, "std": 0.018104055404219846 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7398516857843707, "std": 0.011985126504634338 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7322166213591226, "std": 0.01436502555464267 } ] } }, { "slug": "hospital-readmission", "dataset": "Diabetes130US", "domain": "health", "sourceUrl": "https://www.openml.org/d/46922", "originalSource": "https://doi.org/10.24432/C5230J", "attribution": "Hospital readmission dataset. Original source and curated OpenML task linked below.", "rows": 71518, "features": 47, "target": "EarlyReadmission", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.6792849726798769, "std": 0.008092235655402425 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.6722717030582201, "std": 0.007568730146706635, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.007013269621656715, "relativeChange": 1.04321951820265, "reductionPercent": null, "headline": { "value": "0.70 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.6792849726798769, "std": 0.008092235655402425, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.6722717030582201, "std": 0.007568730146706635, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.6717190038583764, "std": 0.007989308190930152, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.6695729738822368, "std": 0.008063462583593075, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.6585527888789311, "std": 0.008223470961317996, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.6572957146703649, "std": 0.0077998937332656735, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.652367626970675, "std": 0.007894390399822827, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6512162975948141, "std": 0.00612006613614583, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.6792849726798769, "std": 0.008092235655402425 }, { "family": "CAT", "name": "CatBoost", "mean": 0.6711102070089774, "std": 0.007877119882451713 }, { "family": "GBM", "name": "LightGBM", "mean": 0.648238143916597, "std": 0.007512924226713874 }, { "family": "XGB", "name": "XGBoost", "mean": 0.6620626835953676, "std": 0.00795225173806358 }, { "family": "RF", "name": "Random forest", "mean": 0.6308007872355369, "std": 0.0063169303499334434 }, { "family": "XT", "name": "Extra trees", "mean": 0.6287123243242752, "std": 0.00720107435507355 }, { "family": "LR", "name": "Logistic regression", "mean": 0.6480149861607528, "std": 0.007704816148929556 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.5418306968821753, "std": 0.005776141276182463 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.6792849726798769, "std": 0.008092235655402425 }, { "family": "CAT", "name": "CatBoost", "mean": 0.6708760212458346, "std": 0.007996400847456736 }, { "family": "GBM", "name": "LightGBM", "mean": 0.6677382660869144, "std": 0.006520488646604981 }, { "family": "XGB", "name": "XGBoost", "mean": 0.668034875509657, "std": 0.008075219961651956 }, { "family": "RF", "name": "Random forest", "mean": 0.655794964778093, "std": 0.008453007132557864 }, { "family": "XT", "name": "Extra trees", "mean": 0.6492689389666703, "std": 0.007687594133942589 }, { "family": "LR", "name": "Logistic regression", "mean": 0.6581526706949445, "std": 0.008386353448345586 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6332543499773855, "std": 0.005213573492843402 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.6792849726798769, "std": 0.008092235655402425 }, { "family": "CAT", "name": "CatBoost", "mean": 0.6717190038583764, "std": 0.007989308190930152 }, { "family": "GBM", "name": "LightGBM", "mean": 0.6722717030582201, "std": 0.007568730146706635 }, { "family": "XGB", "name": "XGBoost", "mean": 0.6695729738822368, "std": 0.008063462583593075 }, { "family": "RF", "name": "Random forest", "mean": 0.6572957146703649, "std": 0.0077998937332656735 }, { "family": "XT", "name": "Extra trees", "mean": 0.652367626970675, "std": 0.007894390399822827 }, { "family": "LR", "name": "Logistic regression", "mean": 0.6585527888789311, "std": 0.008223470961317996 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6512162975948141, "std": 0.00612006613614583 } ] } }, { "slug": "diabetes-test-outcomes", "dataset": "diabetes", "domain": "health", "sourceUrl": "https://www.openml.org/d/46921", "originalSource": "https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database", "attribution": "Diabetes test outcomes dataset. Original source and curated OpenML task linked below.", "rows": 768, "features": 8, "target": "TestedPositiveForDiabetes", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.838807589309746, "std": 0.02229899665300301 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.8377585925872485, "std": 0.02584247867859371, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": 0.001048996722497475, "relativeChange": 0.12521467780567433, "reductionPercent": null, "headline": { "value": "0.10 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.838807589309746, "std": 0.02229899665300301, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.8377585925872485, "std": 0.02584247867859371, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.836477591272939, "std": 0.02233139175103659, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "CAT", "name": "CatBoost", "mean": 0.8348041624135571, "std": 0.023699569125154085, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.8318663552818554, "std": 0.023785470368010195, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.831563452521277, "std": 0.023823938438261267, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8296225284791336, "std": 0.024984726386967, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8232790982119812, "std": 0.02519155154101567, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.838807589309746, "std": 0.02229899665300301 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8337350619519651, "std": 0.023883354178852702 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8288710836978631, "std": 0.024700734600841733 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8240343757831268, "std": 0.024264099463795985 }, { "family": "RF", "name": "Random forest", "mean": 0.8245150835912219, "std": 0.022734383417293457 }, { "family": "XT", "name": "Extra trees", "mean": 0.8295729349627685, "std": 0.022474821881661142 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8318663552818554, "std": 0.023785470368010195 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8106014328456935, "std": 0.02264719312959134 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.838807589309746, "std": 0.02229899665300301 }, { "family": "CAT", "name": "CatBoost", "mean": 0.834347274795955, "std": 0.024004101027946752 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8377585925872485, "std": 0.02584247867859371 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8300358919962221, "std": 0.02441330140113199 }, { "family": "RF", "name": "Random forest", "mean": 0.8296225284791336, "std": 0.024984726386967 }, { "family": "XT", "name": "Extra trees", "mean": 0.836477591272939, "std": 0.02233139175103659 }, { "family": "LR", "name": "Logistic regression", "mean": 0.830261687716125, "std": 0.022737537864105265 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8232790982119812, "std": 0.02519155154101567 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.838807589309746, "std": 0.02229899665300301 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8348041624135571, "std": 0.023699569125154085 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8374081291563047, "std": 0.02508066469765235 }, { "family": "XGB", "name": "XGBoost", "mean": 0.831563452521277, "std": 0.023823938438261267 }, { "family": "RF", "name": "Random forest", "mean": 0.8295073415283057, "std": 0.02357524757396198 }, { "family": "XT", "name": "Extra trees", "mean": 0.836455510980656, "std": 0.021523711669305005 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8309961855090415, "std": 0.023246874937146386 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8227652241806416, "std": 0.025469233582807983 } ] } }, { "slug": "blood-donation-return", "dataset": "blood-transfusion-service-center", "domain": "health", "sourceUrl": "https://www.openml.org/d/46913", "originalSource": "https://doi.org/10.24432/C5GS39", "attribution": "Blood donation return dataset. Original source and curated OpenML task linked below.", "rows": 748, "features": 4, "target": "DonatedBloodInMarch2007", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.752814228367529, "std": 0.031037649161216 }, "strongestConventional": { "family": "LR", "name": "Logistic regression", "mean": 0.7543991228070175, "std": 0.025627723048312172, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": -0.0015848944394885045, "relativeChange": -0.2100869939497445, "reductionPercent": null, "headline": { "value": "0.16 pp", "label": "lower ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.752814228367529, "std": 0.031037649161216, "configuration": "default", "configurationLabel": "default" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7543991228070175, "std": 0.025627723048312172, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7429681088314005, "std": 0.030805798656275977, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7381589602537417, "std": 0.03027679138958421, "configuration": "default", "configurationLabel": "default" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7356722172663297, "std": 0.034226050699489946, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.7345987461591833, "std": 0.03101080912141111, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7328897313906234, "std": 0.031411916336633365, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "RF", "name": "Random forest", "mean": 0.7144164684309644, "std": 0.028754168572454754, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.752814228367529, "std": 0.031037649161216 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7381589602537417, "std": 0.03027679138958421 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7259572058677768, "std": 0.033038200481022933 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7082736148280305, "std": 0.03033299760634575 }, { "family": "RF", "name": "Random forest", "mean": 0.6820179155515909, "std": 0.025686020157857245 }, { "family": "XT", "name": "Extra trees", "mean": 0.694156209733373, "std": 0.024630215017036782 }, { "family": "LR", "name": "Logistic regression", "mean": 0.731228590544157, "std": 0.032221074299382806 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6880382594905342, "std": 0.02330665559214617 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.752814228367529, "std": 0.031037649161216 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7373390573892358, "std": 0.03046739853977139 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7429095797403112, "std": 0.032848820777315255 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7328897313906234, "std": 0.031411916336633365 }, { "family": "RF", "name": "Random forest", "mean": 0.7144164684309644, "std": 0.028754168572454754 }, { "family": "XT", "name": "Extra trees", "mean": 0.7345987461591833, "std": 0.03101080912141111 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7486644117355535, "std": 0.02927388405338951 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7269414709089107, "std": 0.033104744247636854 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.752814228367529, "std": 0.031037649161216 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7380704480126871, "std": 0.03044368490156301 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7429681088314005, "std": 0.030805798656275977 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7310273317474477, "std": 0.030642313550108196 }, { "family": "RF", "name": "Random forest", "mean": 0.7133952572108236, "std": 0.028785749166571097 }, { "family": "XT", "name": "Extra trees", "mean": 0.7298791505600158, "std": 0.028391345596698446 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7543991228070175, "std": 0.025627723048312172 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7356722172663297, "std": 0.034226050699489946 } ] } }, { "slug": "maternal-health-risk-categories", "dataset": "maternal_health_risk", "domain": "health", "sourceUrl": "https://www.openml.org/d/46941", "originalSource": "https://doi.org/10.24432/C5DP5D", "attribution": "Maternal health risk categories dataset. Original source and curated OpenML task linked below.", "rows": 1014, "features": 6, "target": "RiskLevel", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.3882246007521947, "std": 0.04885793183883319 }, "strongestConventional": { "family": "XT", "name": "Extra trees", "mean": 0.4399336446012541, "std": 0.05457118497862392, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.05170904384905939, "relativeChange": 11.753827988292937, "reductionPercent": 11.753827988292937, "headline": { "value": "11.8%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.3882246007521947, "std": 0.04885793183883319, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.4399336446012541, "std": 0.05457118497862392, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.4483534788622565, "std": 0.05361247210431271, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.4586789865665083, "std": 0.05138778164076062, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "CAT", "name": "CatBoost", "mean": 0.46038397171133544, "std": 0.049137880149512064, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.4609593549234095, "std": 0.04549039337405965, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.4636359949906667, "std": 0.06235533641802802, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7839656750361125, "std": 0.037426719007488, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.3882246007521947, "std": 0.04885793183883319 }, { "family": "CAT", "name": "CatBoost", "mean": 0.47707251453803556, "std": 0.0540748739509916 }, { "family": "GBM", "name": "LightGBM", "mean": 0.48818143462470354, "std": 0.05154183698991059 }, { "family": "XGB", "name": "XGBoost", "mean": 0.46984478827258447, "std": 0.05117402018253237 }, { "family": "RF", "name": "Random forest", "mean": 0.47875600565079335, "std": 0.0714250104842431 }, { "family": "XT", "name": "Extra trees", "mean": 0.47472502499827585, "std": 0.06377732373306584 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7963017009163248, "std": 0.03658718667616511 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.937701641591039, "std": 0.23557860688299243 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.3882246007521947, "std": 0.04885793183883319 }, { "family": "CAT", "name": "CatBoost", "mean": 0.4649685973913481, "std": 0.052653592863029064 }, { "family": "GBM", "name": "LightGBM", "mean": 0.4617535444194936, "std": 0.04875731508321015 }, { "family": "XGB", "name": "XGBoost", "mean": 0.4586789865665083, "std": 0.05138778164076062 }, { "family": "RF", "name": "Random forest", "mean": 0.47045172867999374, "std": 0.05281518921723954 }, { "family": "XT", "name": "Extra trees", "mean": 0.45191151011462183, "std": 0.05526164384413856 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7932747999827067, "std": 0.03847516435191686 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8096405406792958, "std": 0.126359334286916 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.3882246007521947, "std": 0.04885793183883319 }, { "family": "CAT", "name": "CatBoost", "mean": 0.46038397171133544, "std": 0.049137880149512064 }, { "family": "GBM", "name": "LightGBM", "mean": 0.4609593549234095, "std": 0.04549039337405965 }, { "family": "XGB", "name": "XGBoost", "mean": 0.461899929957564, "std": 0.04986062314397886 }, { "family": "RF", "name": "Random forest", "mean": 0.4483534788622565, "std": 0.05361247210431271 }, { "family": "XT", "name": "Extra trees", "mean": 0.4399336446012541, "std": 0.05457118497862392 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7839656750361125, "std": 0.037426719007488 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.4636359949906667, "std": 0.06235533641802802 } ] } }, { "slug": "myocardial-infarction-outcomes", "dataset": "MIC", "domain": "health", "sourceUrl": "https://www.openml.org/d/46980", "originalSource": "https://doi.org/10.24432/C53P5M", "attribution": "Myocardial infarction outcomes dataset. Original source and curated OpenML task linked below.", "rows": 1699, "features": 111, "target": "LET_IS", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.42242917120456697, "std": 0.019385310655327476 }, "strongestConventional": { "family": "XGB", "name": "XGBoost", "mean": 0.4395940177948042, "std": 0.01901989682935627, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.01716484659023726, "relativeChange": 3.904704317029525, "reductionPercent": 3.904704317029525, "headline": { "value": "3.9%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.42242917120456697, "std": 0.019385310655327476, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.4395940177948042, "std": 0.01901989682935627, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.4515746646800397, "std": 0.018599619929335696, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.45309588715171584, "std": 0.020296256244617863, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.4677952915430069, "std": 0.021146599387419262, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.4685969291529418, "std": 0.017288868113133602, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.47363503257664386, "std": 0.018754922461933908, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.5826117336750031, "std": 0.019029124735789788, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.42242917120456697, "std": 0.019385310655327476 }, { "family": "CAT", "name": "CatBoost", "mean": 0.4548963095106775, "std": 0.019948840218430144 }, { "family": "GBM", "name": "LightGBM", "mean": 0.5028670559482501, "std": 0.019279282065822204 }, { "family": "XGB", "name": "XGBoost", "mean": 0.47002681795934703, "std": 0.020161483658659444 }, { "family": "RF", "name": "Random forest", "mean": 0.5127038068026739, "std": 0.03089750375347811 }, { "family": "XT", "name": "Extra trees", "mean": 0.48377965559483627, "std": 0.014925271548227927 }, { "family": "LR", "name": "Logistic regression", "mean": 0.5889248463467165, "std": 0.035386554078310505 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 1.4770621189971782, "std": 0.0960459267573383 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.42242917120456697, "std": 0.019385310655327476 }, { "family": "CAT", "name": "CatBoost", "mean": 0.45424808023367486, "std": 0.01965120513248105 }, { "family": "GBM", "name": "LightGBM", "mean": 0.45309588715171584, "std": 0.020296256244617863 }, { "family": "XGB", "name": "XGBoost", "mean": 0.4399962983867948, "std": 0.01918112103868553 }, { "family": "RF", "name": "Random forest", "mean": 0.4847023665981328, "std": 0.022954137703744912 }, { "family": "XT", "name": "Extra trees", "mean": 0.48133239381076365, "std": 0.01835937611747507 }, { "family": "LR", "name": "Logistic regression", "mean": 0.4686221460501353, "std": 0.02095351490448944 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6569735467433929, "std": 0.024925356399253848 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.42242917120456697, "std": 0.019385310655327476 }, { "family": "CAT", "name": "CatBoost", "mean": 0.4515746646800397, "std": 0.018599619929335696 }, { "family": "GBM", "name": "LightGBM", "mean": 0.45330382768075794, "std": 0.018696345747022003 }, { "family": "XGB", "name": "XGBoost", "mean": 0.4395940177948042, "std": 0.01901989682935627 }, { "family": "RF", "name": "Random forest", "mean": 0.47363503257664386, "std": 0.018754922461933908 }, { "family": "XT", "name": "Extra trees", "mean": 0.4685969291529418, "std": 0.017288868113133602 }, { "family": "LR", "name": "Logistic regression", "mean": 0.4677952915430069, "std": 0.021146599387419262 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.5826117336750031, "std": 0.019029124735789788 } ] } }, { "slug": "medical-insurance-expenses", "dataset": "healthcare_insurance_expenses", "domain": "health", "sourceUrl": "https://www.openml.org/d/46931", "originalSource": "https://www.kaggle.com/datasets/arunjangir245/healthcare-insurance-expenses/", "attribution": "Medical insurance expenses dataset. Original source and curated OpenML task linked below.", "rows": 1338, "features": 6, "target": "charges", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 4393.1220136577695, "std": 318.61400222645045 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 4511.904014215393, "std": 325.4527213384148, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 118.78200055762318, "relativeChange": 2.632635804826159, "reductionPercent": 2.632635804826159, "headline": { "value": "2.6%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 4393.1220136577695, "std": 318.61400222645045, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 4511.904014215393, "std": 325.4527213384148, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 4519.582092691704, "std": 320.2099060289953, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 4520.002440789901, "std": 322.5212826803379, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 4601.995483278476, "std": 322.32749915615244, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 4629.600649064786, "std": 302.9389665372432, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 5024.40848725001, "std": 319.8219924622138, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 6083.358793025874, "std": 275.8648082262347, "configuration": "default", "configurationLabel": "default" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 4393.1220136577695, "std": 318.61400222645045 }, { "family": "CAT", "name": "CatBoost", "mean": 4528.167150592409, "std": 324.4790497359684 }, { "family": "GBM", "name": "LightGBM", "mean": 4610.37746116221, "std": 313.82447879732655 }, { "family": "XGB", "name": "XGBoost", "mean": 4671.9857621558, "std": 306.27973194721653 }, { "family": "RF", "name": "Random forest", "mean": 4888.5052065272885, "std": 289.21897514046805 }, { "family": "XT", "name": "Extra trees", "mean": 4787.04355446557, "std": 282.74300910708234 }, { "family": "LR", "name": "Linear regression", "mean": 6083.358793025874, "std": 275.8648082262347 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 5797.45439974332, "std": 392.8666663438347 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 4393.1220136577695, "std": 318.61400222645045 }, { "family": "CAT", "name": "CatBoost", "mean": 4520.002440789901, "std": 322.5212826803379 }, { "family": "GBM", "name": "LightGBM", "mean": 4525.101549621857, "std": 329.1937452505643 }, { "family": "XGB", "name": "XGBoost", "mean": 4523.348466565101, "std": 319.7376586531918 }, { "family": "RF", "name": "Random forest", "mean": 4641.090939410833, "std": 303.56880127057883 }, { "family": "XT", "name": "Extra trees", "mean": 4603.176886695504, "std": 321.26340083984314 }, { "family": "LR", "name": "Linear regression", "mean": 6085.450334951116, "std": 275.802978072802 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 5058.719878570579, "std": 315.4885574229843 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 4393.1220136577695, "std": 318.61400222645045 }, { "family": "CAT", "name": "CatBoost", "mean": 4522.386211169526, "std": 321.12171815381726 }, { "family": "GBM", "name": "LightGBM", "mean": 4511.904014215393, "std": 325.4527213384148 }, { "family": "XGB", "name": "XGBoost", "mean": 4519.582092691704, "std": 320.2099060289953 }, { "family": "RF", "name": "Random forest", "mean": 4629.600649064786, "std": 302.9389665372432 }, { "family": "XT", "name": "Extra trees", "mean": 4601.995483278476, "std": 322.32749915615244 }, { "family": "LR", "name": "Linear regression", "mean": 6084.501132519176, "std": 276.6272213775384 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 5024.40848725001, "std": 319.8219924622138 } ] } }, { "slug": "truck-air-pressure-failures", "dataset": "APSFailure", "domain": "operations", "sourceUrl": "https://www.openml.org/d/46908", "originalSource": "https://doi.org/10.24432/C5V60Q", "attribution": "Truck air-pressure system failures dataset. Original source and curated OpenML task linked below.", "rows": 76000, "features": 170, "target": "AirPressureSystemFailure", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9949221299813223, "std": 0.0018909493554637388 }, "strongestConventional": { "family": "XGB", "name": "XGBoost", "mean": 0.9924752948069293, "std": 0.001869331391131794, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.002446835174393036, "relativeChange": 0.24653864808484025, "reductionPercent": null, "headline": { "value": "0.24 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9949221299813223, "std": 0.0018909493554637388, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9924752948069293, "std": 0.001869331391131794, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9924425101727428, "std": 0.002718767363996976, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9923191498375111, "std": 0.0021696100392430986, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.9911367815091288, "std": 0.002394012567486992, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.990355341021773, "std": 0.002244521609949889, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9896953704642596, "std": 0.0015164407897066761, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9896048242128189, "std": 0.0012608083565558142, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9949221299813223, "std": 0.0018909493554637388 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9924425101727428, "std": 0.002718767363996976 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9919115677669637, "std": 0.0021873078087597006 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9921344865913225, "std": 0.0018979256244558277 }, { "family": "RF", "name": "Random forest", "mean": 0.9897501903613622, "std": 0.0023734083506121405 }, { "family": "XT", "name": "Extra trees", "mean": 0.9904233386076492, "std": 0.0022935334673075667 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9877529306725658, "std": 0.0024490033155930343 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9604712182783497, "std": 0.005225599006150038 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9949221299813223, "std": 0.0018909493554637388 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9918401302505441, "std": 0.002783885270950975 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9920147207014428, "std": 0.0021171418033144925 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9922844147725867, "std": 0.0019765080923112386 }, { "family": "RF", "name": "Random forest", "mean": 0.9897501903613622, "std": 0.0023734083506120928 }, { "family": "XT", "name": "Extra trees", "mean": 0.990058565298238, "std": 0.0016157640735021868 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9881213918650174, "std": 0.002055757627866324 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9849105126647616, "std": 0.001827716711585539 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9949221299813223, "std": 0.0018909493554637388 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9920144618381437, "std": 0.0027783394732878866 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9923191498375111, "std": 0.0021696100392430986 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9924752948069293, "std": 0.001869331391131794 }, { "family": "RF", "name": "Random forest", "mean": 0.990355341021773, "std": 0.002244521609949889 }, { "family": "XT", "name": "Extra trees", "mean": 0.9911367815091288, "std": 0.002394012567486992 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9896048242128189, "std": 0.0012608083565558142 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9896953704642596, "std": 0.0015164407897066761 } ] } }, { "slug": "ecommerce-delivery-delays", "dataset": "E-CommereShippingData", "domain": "operations", "sourceUrl": "https://www.openml.org/d/46924", "originalSource": "https://www.kaggle.com/datasets/prachi13/customer-analytics", "attribution": "E-commerce delivery delays dataset. Original source and curated OpenML task linked below.", "rows": 10999, "features": 10, "target": "ArrivedLate", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7469126518180645, "std": 0.006037484979811628 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.7444397605063252, "std": 0.0061588893995908394, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.0024728913117393336, "relativeChange": 0.33218151997381423, "reductionPercent": null, "headline": { "value": "0.25 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7469126518180645, "std": 0.006037484979811628, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7444397605063252, "std": 0.0061588893995908394, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7419757965976448, "std": 0.006771799389426941, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.741618383052879, "std": 0.0054197403783186925, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7414143335267586, "std": 0.00555163068248925, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7412155168226574, "std": 0.0053510415267421455, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7361970274800081, "std": 0.008359334092344095, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7224763434277386, "std": 0.0077566611870235795, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7469126518180645, "std": 0.006037484979811628 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7444397605063252, "std": 0.0061588893995908394 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7393429119724536, "std": 0.005822568438122795 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7396443180579844, "std": 0.006080631626739158 }, { "family": "RF", "name": "Random forest", "mean": 0.7388291537487642, "std": 0.004717640801437874 }, { "family": "XT", "name": "Extra trees", "mean": 0.7368158038959391, "std": 0.005766236859380994 }, { "family": "LR", "name": "Logistic regression", "mean": 0.703632998237702, "std": 0.006494273013059291 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7028284907444868, "std": 0.005661682776481184 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7469126518180645, "std": 0.006037484979811628 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7428434860968434, "std": 0.00811274765253404 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7400369194942862, "std": 0.0050764671564375845 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7419757965976448, "std": 0.006771799389426941 }, { "family": "RF", "name": "Random forest", "mean": 0.7397126280087317, "std": 0.005843466073757184 }, { "family": "XT", "name": "Extra trees", "mean": 0.741618383052879, "std": 0.0054197403783186925 }, { "family": "LR", "name": "Logistic regression", "mean": 0.721616770090954, "std": 0.008068659743348498 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7361970274800081, "std": 0.008359334092344095 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7469126518180645, "std": 0.006037484979811628 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7423775287476537, "std": 0.006599586577579785 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7414143335267586, "std": 0.00555163068248925 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7418740453015021, "std": 0.00623356942826915 }, { "family": "RF", "name": "Random forest", "mean": 0.7412155168226574, "std": 0.0053510415267421455 }, { "family": "XT", "name": "Extra trees", "mean": 0.7412642706178609, "std": 0.005853138820883086 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7224763434277386, "std": 0.0077566611870235795 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7326015006897046, "std": 0.0047772157443623335 } ] } }, { "slug": "food-delivery-duration", "dataset": "Food_Delivery_Time", "domain": "operations", "sourceUrl": "https://www.openml.org/d/46928", "originalSource": "https://www.kaggle.com/datasets/rajatkumar30/food-delivery-time", "attribution": "Food delivery duration dataset. Original source and curated OpenML task linked below.", "rows": 45451, "features": 9, "target": "Time_taken(min)", "targetUnit": "min", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 7.378259870741102, "std": 0.04368609729296416 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 7.366906313834033, "std": 0.050249221309773176, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": -0.011353556907069517, "relativeChange": -0.15411566841496416, "reductionPercent": -0.15411566841496416, "headline": { "value": "0.2%", "label": "higher prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 7.378259870741102, "std": 0.04368609729296416, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 7.366906313834033, "std": 0.050249221309773176, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 7.374088565629113, "std": 0.052639342837972294, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 7.397219869825575, "std": 0.05534085196062395, "configuration": "default", "configurationLabel": "default" }, { "family": "RF", "name": "Random forest", "mean": 7.586524377358717, "std": 0.04613616895597316, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 7.756498125193129, "std": 0.05255249204666232, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 7.90884561653402, "std": 0.04911882134334895, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 8.277214031146631, "std": 0.054610692163166295, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 7.378259870741102, "std": 0.04368609729296416 }, { "family": "CAT", "name": "CatBoost", "mean": 7.379068056742351, "std": 0.05243388987093891 }, { "family": "GBM", "name": "LightGBM", "mean": 7.615609169006348, "std": 0.05337916868232682 }, { "family": "XGB", "name": "XGBoost", "mean": 7.397219869825575, "std": 0.05534085196062395 }, { "family": "RF", "name": "Random forest", "mean": 7.855453862084283, "std": 0.041403488048149355 }, { "family": "XT", "name": "Extra trees", "mean": 8.111618359883627, "std": 0.049766081652615715 }, { "family": "LR", "name": "Linear regression", "mean": 8.563568751017252, "std": 0.04674810514386582 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 8.562770631578234, "std": 0.04214798925427141 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 7.378259870741102, "std": 0.04368609729296416 }, { "family": "CAT", "name": "CatBoost", "mean": 7.366906313834033, "std": 0.050249221309773176 }, { "family": "GBM", "name": "LightGBM", "mean": 7.378250010217051, "std": 0.05356700737648888 }, { "family": "XGB", "name": "XGBoost", "mean": 7.397219912731476, "std": 0.05534089013613288 }, { "family": "RF", "name": "Random forest", "mean": 7.586524377358717, "std": 0.04613616895597316 }, { "family": "XT", "name": "Extra trees", "mean": 7.765972261740505, "std": 0.05415442506062197 }, { "family": "LR", "name": "Linear regression", "mean": 8.3398499946884, "std": 0.06318905344893333 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 8.041855823763475, "std": 0.0477757653664788 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 7.378259870741102, "std": 0.04368609729296416 }, { "family": "CAT", "name": "CatBoost", "mean": 7.367079250866535, "std": 0.05101181733013693 }, { "family": "GBM", "name": "LightGBM", "mean": 7.374088565629113, "std": 0.052639342837972294 }, { "family": "XGB", "name": "XGBoost", "mean": 7.400482060283884, "std": 0.054683434076190404 }, { "family": "RF", "name": "Random forest", "mean": 7.588245784385813, "std": 0.04634679088040818 }, { "family": "XT", "name": "Extra trees", "mean": 7.756498125193129, "std": 0.05255249204666232 }, { "family": "LR", "name": "Linear regression", "mean": 8.277214031146631, "std": 0.054610692163166295 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 7.90884561653402, "std": 0.04911882134334895 } ] } }, { "slug": "steel-product-classification", "dataset": "anneal", "domain": "operations", "sourceUrl": "https://www.openml.org/d/46906", "originalSource": "https://doi.org/10.24432/C5RW2F", "attribution": "Steel product classification dataset. Original source and curated OpenML task linked below.", "rows": 898, "features": 38, "target": "classes", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.013097201408042262, "std": 0.013743946336420388 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.02163693607347795, "std": 0.020712860005499108, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.008539734665435686, "relativeChange": 39.46831767878398, "reductionPercent": 39.46831767878398, "headline": { "value": "39.5%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.013097201408042262, "std": 0.013743946336420388, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.02163693607347795, "std": 0.020712860005499108, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.02292420721408463, "std": 0.013122037512842754, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.023276548134778287, "std": 0.01597320867892719, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.030814712620874717, "std": 0.02517827860103919, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 0.032668474137418455, "std": 0.019432377742480283, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.03654924777025978, "std": 0.02391971510376011, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.06199751459062099, "std": 0.040000909481135286, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.013097201408042262, "std": 0.013743946336420388 }, { "family": "CAT", "name": "CatBoost", "mean": 0.03890469920813705, "std": 0.021625920463585625 }, { "family": "GBM", "name": "LightGBM", "mean": 0.05530609389149624, "std": 0.02612575294511163 }, { "family": "XGB", "name": "XGBoost", "mean": 0.0388454608042337, "std": 0.024704819032275276 }, { "family": "RF", "name": "Random forest", "mean": 0.04632735277813608, "std": 0.010102362876210257 }, { "family": "XT", "name": "Extra trees", "mean": 0.07056164203939362, "std": 0.011998019320344024 }, { "family": "LR", "name": "Logistic regression", "mean": 0.08951194614441528, "std": 0.027535143492218334 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.15123075599767052, "std": 0.04318685271800655 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.013097201408042262, "std": 0.013743946336420388 }, { "family": "CAT", "name": "CatBoost", "mean": 0.022192019722805625, "std": 0.021187763058379997 }, { "family": "GBM", "name": "LightGBM", "mean": 0.032668474137418455, "std": 0.019432377742480283 }, { "family": "XGB", "name": "XGBoost", "mean": 0.030814712620874717, "std": 0.02517827860103919 }, { "family": "RF", "name": "Random forest", "mean": 0.028467861062720933, "std": 0.02543003862279287 }, { "family": "XT", "name": "Extra trees", "mean": 0.024965594332683187, "std": 0.015109320322924918 }, { "family": "LR", "name": "Logistic regression", "mean": 0.045848104466373725, "std": 0.032140864701179654 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.07998327035456895, "std": 0.046373999920023355 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.013097201408042262, "std": 0.013743946336420388 }, { "family": "CAT", "name": "CatBoost", "mean": 0.02163693607347795, "std": 0.020712860005499108 }, { "family": "GBM", "name": "LightGBM", "mean": 0.03369580257268579, "std": 0.019442821868596836 }, { "family": "XGB", "name": "XGBoost", "mean": 0.03098065468889255, "std": 0.02488009144484039 }, { "family": "RF", "name": "Random forest", "mean": 0.02292420721408463, "std": 0.013122037512842754 }, { "family": "XT", "name": "Extra trees", "mean": 0.023276548134778287, "std": 0.01597320867892719 }, { "family": "LR", "name": "Logistic regression", "mean": 0.03654924777025978, "std": 0.02391971510376011 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.06199751459062099, "std": 0.040000909481135286 } ] } }, { "slug": "food-contaminant-detection", "dataset": "hazelnut-spread-contaminant-detection", "domain": "operations", "sourceUrl": "https://www.openml.org/d/46930", "originalSource": "https://www.openml.org/d/45538", "attribution": "Food contaminant detection dataset. Original source and curated OpenML task linked below.", "rows": 2400, "features": 30, "target": "Contaminated", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9952885416666667, "std": 0.001373998541388775 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.977795, "std": 0.003556434037114262, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": 0.017493541666666723, "relativeChange": 1.7890807036921568, "reductionPercent": null, "headline": { "value": "1.75 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9952885416666667, "std": 0.001373998541388775, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.977795, "std": 0.003556434037114262, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9754295833333333, "std": 0.003778913296706216, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9749189583333333, "std": 0.004281536921965308, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.9646709375, "std": 0.005080239788427338, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.9601561458333333, "std": 0.0058472212447086775, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9525761458333333, "std": 0.0058597922255668716, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9434390625, "std": 0.007833808687993054, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9952885416666667, "std": 0.001373998541388775 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9741947916666667, "std": 0.0042833925495006624 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9726860416666667, "std": 0.004618515865739044 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9731502083333333, "std": 0.004806416464801811 }, { "family": "RF", "name": "Random forest", "mean": 0.9578964583333334, "std": 0.005904266151801385 }, { "family": "XT", "name": "Extra trees", "mean": 0.9536296875, "std": 0.006230941672476836 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9482581250000001, "std": 0.006379717268810329 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9136259375, "std": 0.009403345050269574 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9952885416666667, "std": 0.001373998541388775 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9749189583333333, "std": 0.004281536921965308 }, { "family": "GBM", "name": "LightGBM", "mean": 0.977795, "std": 0.003556434037114262 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9754295833333333, "std": 0.003778913296706216 }, { "family": "RF", "name": "Random forest", "mean": 0.9592955208333334, "std": 0.005768237375613632 }, { "family": "XT", "name": "Extra trees", "mean": 0.9643546875, "std": 0.005333321629653895 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9519714583333333, "std": 0.006063570755809161 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9343958333333333, "std": 0.008557533692735245 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9952885416666667, "std": 0.001373998541388775 }, { "family": "CAT", "name": "CatBoost", "mean": 0.973935625, "std": 0.004363551878299602 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9777866666666667, "std": 0.0037719550309815663 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9753089583333333, "std": 0.0038901974243422646 }, { "family": "RF", "name": "Random forest", "mean": 0.9601561458333333, "std": 0.0058472212447086775 }, { "family": "XT", "name": "Extra trees", "mean": 0.9646709375, "std": 0.005080239788427338 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9525761458333333, "std": 0.0058597922255668716 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9434390625, "std": 0.007833808687993054 } ] } }, { "slug": "mining-seismic-events", "dataset": "seismic-bumps", "domain": "operations", "sourceUrl": "https://www.openml.org/d/46956", "originalSource": "https://doi.org/10.24432/C5W902", "attribution": "Mining seismic events dataset. Original source and curated OpenML task linked below.", "rows": 2584, "features": 15, "target": "HighEnergySeismicBump", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7863086403747351, "std": 0.023150871738132652 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.7726793709515765, "std": 0.025878447009482792, "configuration": "default", "configurationLabel": "default" }, "signedDifference": 0.013629269423158674, "relativeChange": 1.7638971526279839, "reductionPercent": null, "headline": { "value": "1.36 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7863086403747351, "std": 0.023150871738132652, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7726793709515765, "std": 0.025878447009482792, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.7722985136412442, "std": 0.02952339350576921, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7714261300162499, "std": 0.025741394445227394, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7706749852039463, "std": 0.024841766607095937, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7666702479497365, "std": 0.02226029141425023, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.764073637659655, "std": 0.027536982014246317, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.76260393218212, "std": 0.024748091599313574, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7863086403747351, "std": 0.023150871738132652 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7726793709515765, "std": 0.025878447009482792 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7524495422235189, "std": 0.026793971029113788 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7585130278201779, "std": 0.022292814535936414 }, { "family": "RF", "name": "Random forest", "mean": 0.747487259542991, "std": 0.020584398841901795 }, { "family": "XT", "name": "Extra trees", "mean": 0.7426318452578335, "std": 0.02323973895992749 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7586582925524862, "std": 0.024145098573647526 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6850367210270456, "std": 0.033980678217603165 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7863086403747351, "std": 0.023150871738132652 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7702493308764015, "std": 0.026698989417218492 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7695310918317738, "std": 0.026906275546641264 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7678487441492049, "std": 0.024252869077242382 }, { "family": "RF", "name": "Random forest", "mean": 0.7666702479497365, "std": 0.02226029141425023 }, { "family": "XT", "name": "Extra trees", "mean": 0.7722985136412442, "std": 0.02952339350576921 }, { "family": "LR", "name": "Logistic regression", "mean": 0.76122900281065, "std": 0.02286788237610311 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.764073637659655, "std": 0.027536982014246317 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7863086403747351, "std": 0.023150871738132652 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7663857197749928, "std": 0.02765793403112932 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7714261300162499, "std": 0.025741394445227394 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7706749852039463, "std": 0.024841766607095937 }, { "family": "RF", "name": "Random forest", "mean": 0.7649479120695896, "std": 0.02596161138932225 }, { "family": "XT", "name": "Extra trees", "mean": 0.7720931759887033, "std": 0.02355189030659936 }, { "family": "LR", "name": "Logistic regression", "mean": 0.76260393218212, "std": 0.024748091599313574 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7603154291596479, "std": 0.022167187132661213 } ] } }, { "slug": "molecular-biological-response", "dataset": "Bioresponse", "domain": "science", "sourceUrl": "https://www.openml.org/d/46912", "originalSource": "https://www.kaggle.com/c/bioresponse", "attribution": "Molecular biological response dataset. Original source and curated OpenML task linked below.", "rows": 3751, "features": 1776, "target": "MoleculeElicitsResponse", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8845025952606764, "std": 0.008006765313743447 }, "strongestConventional": { "family": "XGB", "name": "XGBoost", "mean": 0.8757075736353408, "std": 0.00778852419286147, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.00879502162533563, "relativeChange": 1.0043331689852466, "reductionPercent": null, "headline": { "value": "0.88 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8845025952606764, "std": 0.008006765313743447, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8757075736353408, "std": 0.00778852419286147, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8755955362929988, "std": 0.00623873487588326, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.87535049501354, "std": 0.007704475610665037, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.874680736500031, "std": 0.008266204722861872, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.8712060128616755, "std": 0.0071191791647955485, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8457009152058497, "std": 0.010160501545510644, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.817130258389969, "std": 0.009391242902385147, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8845025952606764, "std": 0.008006765313743447 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8722887849167792, "std": 0.008067584407205973 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8720542285597345, "std": 0.008247298672305987 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8730889535747526, "std": 0.007963668352592603 }, { "family": "RF", "name": "Random forest", "mean": 0.8728311440853334, "std": 0.007337349915540203 }, { "family": "XT", "name": "Extra trees", "mean": 0.868918646498223, "std": 0.007594138877595377 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7889285891417199, "std": 0.01096609093969899 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8179634603411419, "std": 0.014645622062730896 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8845025952606764, "std": 0.008006765313743447 }, { "family": "CAT", "name": "CatBoost", "mean": 0.874680736500031, "std": 0.008266204722861872 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8743506385719007, "std": 0.0074238383472193005 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8751614101542285, "std": 0.007591977424767023 }, { "family": "RF", "name": "Random forest", "mean": 0.8728311440853334, "std": 0.007337349915540196 }, { "family": "XT", "name": "Extra trees", "mean": 0.868485601127225, "std": 0.007592920128575151 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8101538291695669, "std": 0.00920197374249339 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8372909719127422, "std": 0.010618406692143454 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8845025952606764, "std": 0.008006765313743447 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8742102480133184, "std": 0.008193950678983309 }, { "family": "GBM", "name": "LightGBM", "mean": 0.87535049501354, "std": 0.007704475610665037 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8757075736353408, "std": 0.00778852419286147 }, { "family": "RF", "name": "Random forest", "mean": 0.8755955362929988, "std": 0.00623873487588326 }, { "family": "XT", "name": "Extra trees", "mean": 0.8712060128616755, "std": 0.0071191791647955485 }, { "family": "LR", "name": "Logistic regression", "mean": 0.817130258389969, "std": 0.009391242902385147 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8457009152058497, "std": 0.010160501545510644 } ] } }, { "slug": "compound-activity-classes", "dataset": "hiva_agnostic", "domain": "science", "sourceUrl": "https://www.openml.org/d/46933", "originalSource": "http://www.agnostic.inf.ethz.ch", "attribution": "Compound activity classes dataset. Original source and curated OpenML task linked below.", "rows": 3845, "features": 1617, "target": "CompoundActivity", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.1741339067618052, "std": 0.0003324942036492022 }, "strongestConventional": { "family": "RF", "name": "Random forest", "mean": 0.1738488143748848, "std": 0.0006710083503007765, "configuration": "tuned", "configurationLabel": "tuned" }, "signedDifference": -0.0002850923869203992, "relativeChange": -0.16398868634538427, "reductionPercent": -0.16398868634538427, "headline": { "value": "0.2%", "label": "higher prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1741339067618052, "std": 0.0003324942036492022, "configuration": "default", "configurationLabel": "default" }, { "family": "RF", "name": "Random forest", "mean": 0.1738488143748848, "std": 0.0006710083503007765, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.1738490078787508, "std": 0.0000539142071130112, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "GBM", "name": "LightGBM", "mean": 0.17482102085543133, "std": 0.0005979458794019962, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.17593052923756114, "std": 0.0010478486830123816, "configuration": "default", "configurationLabel": "default" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.17634863158067068, "std": 0.0033944628447668446, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.17934035991065536, "std": 0.0017098788456481745, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.33456024196412826, "std": 0.018797292213745587, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1741339067618052, "std": 0.0003324942036492022 }, { "family": "CAT", "name": "CatBoost", "mean": 0.17593052923756114, "std": 0.0010478486830123816 }, { "family": "GBM", "name": "LightGBM", "mean": 0.17482102085543133, "std": 0.0005979458794019962 }, { "family": "XGB", "name": "XGBoost", "mean": 0.18188102777729867, "std": 0.001844356606317801 }, { "family": "RF", "name": "Random forest", "mean": 0.26332955690095994, "std": 0.025484033830096293 }, { "family": "XT", "name": "Extra trees", "mean": 0.20775193230762218, "std": 0.008708796469369022 }, { "family": "LR", "name": "Logistic regression", "mean": 0.44799278109360197, "std": 0.023780423434266156 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.46831330601466614, "std": 0.016905671708282666 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1741339067618052, "std": 0.0003324942036492022 }, { "family": "CAT", "name": "CatBoost", "mean": 0.17686586287485492, "std": 0.0019177955546627625 }, { "family": "GBM", "name": "LightGBM", "mean": 0.175322742616122, "std": 0.0011766043801505995 }, { "family": "XGB", "name": "XGBoost", "mean": 0.17934035991065536, "std": 0.0017098788456481745 }, { "family": "RF", "name": "Random forest", "mean": 0.1738488143748848, "std": 0.0006710083503007765 }, { "family": "XT", "name": "Extra trees", "mean": 0.1738490078787508, "std": 0.0000539142071130112 }, { "family": "LR", "name": "Logistic regression", "mean": 0.33456024196412826, "std": 0.018797292213745587 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.176448792219162, "std": 0.003482816206130597 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1741339067618052, "std": 0.0003324942036492022 }, { "family": "CAT", "name": "CatBoost", "mean": 0.1770063512988524, "std": 0.0018061087081802619 }, { "family": "GBM", "name": "LightGBM", "mean": 0.17525925336485573, "std": 0.000995636856401228 }, { "family": "XGB", "name": "XGBoost", "mean": 0.17938962567732084, "std": 0.00174874488946148 }, { "family": "RF", "name": "Random forest", "mean": 0.17402442540629523, "std": 0.0005082195683127282 }, { "family": "XT", "name": "Extra trees", "mean": 0.17400520999227945, "std": 0.0002599544224122024 }, { "family": "LR", "name": "Logistic regression", "mean": 0.33456024196412826, "std": 0.018797292213745587 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.17634863158067068, "std": 0.0033944628447668446 } ] } }, { "slug": "molecular-activity-estimation", "dataset": "QSAR-TID-11", "domain": "science", "sourceUrl": "https://www.openml.org/d/46953", "originalSource": "https://www.openml.org/d/3050", "attribution": "Molecular activity estimation dataset. Original source and curated OpenML task linked below.", "rows": 5742, "features": 1024, "target": "MEDIAN_PXC50", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7156708069315537, "std": 0.04638728991898067 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.7557796383261282, "std": 0.04819985976605728, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.04010883139457444, "relativeChange": 5.3069478668949, "reductionPercent": 5.3069478668949, "headline": { "value": "5.3%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7156708069315537, "std": 0.04638728991898067, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7557796383261282, "std": 0.04819985976605728, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7599111122581953, "std": 0.04780094294908637, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7712342213995023, "std": 0.04873239484125627, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.7867739123421451, "std": 0.04648407732119938, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7961444580032255, "std": 0.04584188205969451, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8590694456142886, "std": 0.04738590471012253, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 0.9376198503856692, "std": 0.03947258719148764, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7156708069315537, "std": 0.04638728991898067 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7739495003822704, "std": 0.04824784609316265 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7720785783750831, "std": 0.049772218879092514 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7864762601671922, "std": 0.04870383063029107 }, { "family": "RF", "name": "Random forest", "mean": 0.8062302068409039, "std": 0.04654367193466315 }, { "family": "XT", "name": "Extra trees", "mean": 0.8101844358851091, "std": 0.047895430252404926 }, { "family": "LR", "name": "Linear regression", "mean": 1.0198046593671897, "std": 0.03245186437498427 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 1.002799559723165, "std": 0.042626034130913176 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7156708069315537, "std": 0.04638728991898067 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7736842299200358, "std": 0.04969459878831982 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7583018438972798, "std": 0.04880001533776062 }, { "family": "XGB", "name": "XGBoost", "mean": 0.761035225653962, "std": 0.04716480362888664 }, { "family": "RF", "name": "Random forest", "mean": 0.8051030182558092, "std": 0.047792958058945574 }, { "family": "XT", "name": "Extra trees", "mean": 0.7921892769988511, "std": 0.047732662196289286 }, { "family": "LR", "name": "Linear regression", "mean": 0.939915039849204, "std": 0.039922948391251545 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8876676595584432, "std": 0.04602376812007899 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7156708069315537, "std": 0.04638728991898067 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7712342213995023, "std": 0.04873239484125627 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7557796383261282, "std": 0.04819985976605728 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7599111122581953, "std": 0.04780094294908637 }, { "family": "RF", "name": "Random forest", "mean": 0.7961444580032255, "std": 0.04584188205969451 }, { "family": "XT", "name": "Extra trees", "mean": 0.7867739123421451, "std": 0.04648407732119938 }, { "family": "LR", "name": "Linear regression", "mean": 0.9376198503856692, "std": 0.03947258719148764 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8590694456142886, "std": 0.04738590471012253 } ] } }, { "slug": "chemical-fish-toxicity", "dataset": "QSAR_fish_toxicity", "domain": "science", "sourceUrl": "https://www.openml.org/d/46954", "originalSource": "https://doi.org/10.24432/C5JG7B", "attribution": "Chemical toxicity in fish dataset. Original source and curated OpenML task linked below.", "rows": 907, "features": 6, "target": "LC50", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8521671008982373, "std": 0.04961388754141071 }, "strongestConventional": { "family": "XT", "name": "Extra trees", "mean": 0.8683977214174483, "std": 0.0510999877335672, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.01623062051921098, "relativeChange": 1.869030758477629, "reductionPercent": 1.869030758477629, "headline": { "value": "1.9%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8521671008982373, "std": 0.04961388754141071, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.8683977214174483, "std": 0.0510999877335672, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.8743599763143531, "std": 0.0466784146698192, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8793010445759645, "std": 0.042485401776539373, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.879860066607679, "std": 0.053570081005766074, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.8829055001611016, "std": 0.0441844762139683, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8842614945657162, "std": 0.048857171241253924, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 0.9494987472122333, "std": 0.056021714801491436, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8521671008982373, "std": 0.04961388754141071 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8768961015145907, "std": 0.04841744374289573 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8937979772115074, "std": 0.04320994746437551 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9045708829460707, "std": 0.049506455919158074 }, { "family": "RF", "name": "Random forest", "mean": 0.9074735438704112, "std": 0.0465862851956293 }, { "family": "XT", "name": "Extra trees", "mean": 0.8760257781121997, "std": 0.05203535516760862 }, { "family": "LR", "name": "Linear regression", "mean": 0.9495191370163437, "std": 0.05624259046683071 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8955255863378646, "std": 0.057262017074543765 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8521671008982373, "std": 0.04961388754141071 }, { "family": "CAT", "name": "CatBoost", "mean": 0.876554002197836, "std": 0.04644734467284093 }, { "family": "GBM", "name": "LightGBM", "mean": 0.888529869266558, "std": 0.04519773475936749 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8812353670244638, "std": 0.04289670545938499 }, { "family": "RF", "name": "Random forest", "mean": 0.8850094843975785, "std": 0.04980155001258618 }, { "family": "XT", "name": "Extra trees", "mean": 0.8700359082188431, "std": 0.05141065256652868 }, { "family": "LR", "name": "Linear regression", "mean": 0.9494987472122333, "std": 0.056021714801491436 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8896864399478306, "std": 0.05238787211727514 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8521671008982373, "std": 0.04961388754141071 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8743599763143531, "std": 0.0466784146698192 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8829055001611016, "std": 0.0441844762139683 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8793010445759645, "std": 0.042485401776539373 }, { "family": "RF", "name": "Random forest", "mean": 0.8842614945657162, "std": 0.048857171241253924 }, { "family": "XT", "name": "Extra trees", "mean": 0.8683977214174483, "std": 0.0510999877335672 }, { "family": "LR", "name": "Linear regression", "mean": 0.9501375170245546, "std": 0.05576935949847334 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.879860066607679, "std": 0.053570081005766074 } ] } }, { "slug": "chemical-biodegradability", "dataset": "qsar-biodeg", "domain": "science", "sourceUrl": "https://www.openml.org/d/46952", "originalSource": "https://doi.org/10.24432/C5H60M", "attribution": "Chemical biodegradability dataset. Original source and curated OpenML task linked below.", "rows": 1054, "features": 41, "target": "Biodegradable", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9393035995222997, "std": 0.011984189250796714 }, "strongestConventional": { "family": "XT", "name": "Extra trees", "mean": 0.9338090571938384, "std": 0.012857691250068122, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.005494542328461249, "relativeChange": 0.5884010533130546, "reductionPercent": null, "headline": { "value": "0.55 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9393035995222997, "std": 0.011984189250796714, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.9338090571938384, "std": 0.012857691250068122, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9329895455672631, "std": 0.011531528670046101, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.931669665029029, "std": 0.01144190975870327, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9314587200996642, "std": 0.011814386014025619, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.9296729268560556, "std": 0.012597860145900926, "configuration": "default", "configurationLabel": "default" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9231591858391717, "std": 0.014297327079444887, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9225560595955848, "std": 0.013988596592316334, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9393035995222997, "std": 0.011984189250796714 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9304693827774799, "std": 0.011787249698698979 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9272823568941653, "std": 0.012430126092534004 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9259814160624605, "std": 0.013273969338686102 }, { "family": "RF", "name": "Random forest", "mean": 0.9296729268560556, "std": 0.012597860145900926 }, { "family": "XT", "name": "Extra trees", "mean": 0.9330482036416807, "std": 0.01310147604604776 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9097779011218948, "std": 0.015939953316994854 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9065122637401509, "std": 0.016697923068503304 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9393035995222997, "std": 0.011984189250796714 }, { "family": "CAT", "name": "CatBoost", "mean": 0.93035156741099, "std": 0.012701102435042615 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9328486846837375, "std": 0.011915492450528658 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9312848599103568, "std": 0.012061709102461633 }, { "family": "RF", "name": "Random forest", "mean": 0.9285697526264453, "std": 0.012680677927792315 }, { "family": "XT", "name": "Extra trees", "mean": 0.9323795015933194, "std": 0.012887733751702605 }, { "family": "LR", "name": "Logistic regression", "mean": 0.922969595199686, "std": 0.014306075957135683 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9138150284482747, "std": 0.01498117182044965 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9393035995222997, "std": 0.011984189250796714 }, { "family": "CAT", "name": "CatBoost", "mean": 0.931669665029029, "std": 0.01144190975870327 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9329895455672631, "std": 0.011531528670046101 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9314587200996642, "std": 0.011814386014025619 }, { "family": "RF", "name": "Random forest", "mean": 0.9286953160546971, "std": 0.012780659960865364 }, { "family": "XT", "name": "Extra trees", "mean": 0.9338090571938384, "std": 0.012857691250068122 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9231591858391717, "std": 0.014297327079444887 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9225560595955848, "std": 0.013988596592316334 } ] } }, { "slug": "astronomical-object-classification", "dataset": "SDSS17", "domain": "science", "sourceUrl": "https://www.openml.org/d/46955", "originalSource": "https://www.kaggle.com/datasets/fedesoriano/stellar-classification-dataset-sdss17", "attribution": "Astronomical object classification dataset. Original source and curated OpenML task linked below.", "rows": 78053, "features": 11, "target": "ObjectType", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.0630660326116615, "std": 0.0019042272464029454 }, "strongestConventional": { "family": "RF", "name": "Random forest", "mean": 0.07229429637039804, "std": 0.0019985321592611675, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.009228263758736546, "relativeChange": 12.764857287573234, "reductionPercent": 12.764857287573234, "headline": { "value": "12.8%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.0630660326116615, "std": 0.0019042272464029454, "configuration": "default", "configurationLabel": "default" }, { "family": "RF", "name": "Random forest", "mean": 0.07229429637039804, "std": 0.0019985321592611675, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.07265112494336717, "std": 0.0024166756268038207, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.07359144514879262, "std": 0.0022686611436809204, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.07377837908005737, "std": 0.0025805962916626663, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.0780061499428763, "std": 0.00175834650693597, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.1353071630001068, "std": 0.0021584508192228407, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.15321668651368883, "std": 0.002997995320478138, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.0630660326116615, "std": 0.0019042272464029454 }, { "family": "CAT", "name": "CatBoost", "mean": 0.0752473365928937, "std": 0.002417704782282831 }, { "family": "GBM", "name": "LightGBM", "mean": 0.08707426579828438, "std": 0.002477149599653879 }, { "family": "XGB", "name": "XGBoost", "mean": 0.073875181911539, "std": 0.002361689310672413 }, { "family": "RF", "name": "Random forest", "mean": 0.0852886903759133, "std": 0.0022457051930677087 }, { "family": "XT", "name": "Extra trees", "mean": 0.1290686740766748, "std": 0.0015466633834397433 }, { "family": "LR", "name": "Logistic regression", "mean": 0.14645987884046427, "std": 0.0026651931899661137 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.37997515260466735, "std": 0.030277636681336133 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.0630660326116615, "std": 0.0019042272464029454 }, { "family": "CAT", "name": "CatBoost", "mean": 0.07382676601339583, "std": 0.002751364026973932 }, { "family": "GBM", "name": "LightGBM", "mean": 0.07300846382518358, "std": 0.002649986238492655 }, { "family": "XGB", "name": "XGBoost", "mean": 0.07387518197725858, "std": 0.002361689164749625 }, { "family": "RF", "name": "Random forest", "mean": 0.07256634584878395, "std": 0.0019577236987739425 }, { "family": "XT", "name": "Extra trees", "mean": 0.08086599392542164, "std": 0.0025962700543089062 }, { "family": "LR", "name": "Logistic regression", "mean": 0.14521053267849815, "std": 0.0020435891699656164 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.2238737808333503, "std": 0.0026171364121391947 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.0630660326116615, "std": 0.0019042272464029454 }, { "family": "CAT", "name": "CatBoost", "mean": 0.07377837908005737, "std": 0.0025805962916626663 }, { "family": "GBM", "name": "LightGBM", "mean": 0.07265112494336717, "std": 0.0024166756268038207 }, { "family": "XGB", "name": "XGBoost", "mean": 0.07359144514879262, "std": 0.0022686611436809204 }, { "family": "RF", "name": "Random forest", "mean": 0.07229429637039804, "std": 0.0019985321592611675 }, { "family": "XT", "name": "Extra trees", "mean": 0.0780061499428763, "std": 0.00175834650693597 }, { "family": "LR", "name": "Logistic regression", "mean": 0.1353071630001068, "std": 0.0021584508192228407 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.15321668651368883, "std": 0.002997995320478138 } ] } }, { "slug": "dna-splice-site-classification", "dataset": "splice", "domain": "science", "sourceUrl": "https://www.openml.org/d/46958", "originalSource": "https://doi.org/10.24432/C5M888", "attribution": "DNA splice-site classification dataset. Original source and curated OpenML task linked below.", "rows": 3190, "features": 60, "target": "SiteType", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.09541305568483141, "std": 0.017689412873592346 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 0.10214073276514422, "std": 0.015461760731046686, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.006727677080312813, "relativeChange": 6.586673992032147, "reductionPercent": 6.586673992032147, "headline": { "value": "6.6%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.09541305568483141, "std": 0.017689412873592346, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 0.10214073276514422, "std": 0.015461760731046686, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.10878872850416148, "std": 0.01835350095524407, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "CAT", "name": "CatBoost", "mean": 0.11058823126990487, "std": 0.01857230337460281, "configuration": "default", "configurationLabel": "default" }, { "family": "LR", "name": "Logistic regression", "mean": 0.14764321015940773, "std": 0.011705407096411265, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.17261769910608915, "std": 0.012303760628441027, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.17785348111099128, "std": 0.014184953847596118, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.4469137291113536, "std": 0.02542114836452398, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.09541305568483141, "std": 0.017689412873592346 }, { "family": "CAT", "name": "CatBoost", "mean": 0.11058823126990487, "std": 0.01857230337460281 }, { "family": "GBM", "name": "LightGBM", "mean": 0.11063512976203116, "std": 0.016181129527141964 }, { "family": "XGB", "name": "XGBoost", "mean": 0.11852981241051921, "std": 0.020174156410271524 }, { "family": "RF", "name": "Random forest", "mean": 0.3173723032538566, "std": 0.0050553977542440376 }, { "family": "XT", "name": "Extra trees", "mean": 0.4028277425597682, "std": 0.006110610741205969 }, { "family": "LR", "name": "Logistic regression", "mean": 0.16733092973593539, "std": 0.019414493094324317 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.5512554828132445, "std": 0.01673860661634745 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.09541305568483141, "std": 0.017689412873592346 }, { "family": "CAT", "name": "CatBoost", "mean": 0.11488097672565757, "std": 0.019516075392747568 }, { "family": "GBM", "name": "LightGBM", "mean": 0.10348997238566206, "std": 0.016033614728270102 }, { "family": "XGB", "name": "XGBoost", "mean": 0.10878872850416148, "std": 0.01835350095524407 }, { "family": "RF", "name": "Random forest", "mean": 0.1800567970689514, "std": 0.014986388031478034 }, { "family": "XT", "name": "Extra trees", "mean": 0.17552374869673257, "std": 0.010671614125095395 }, { "family": "LR", "name": "Logistic regression", "mean": 0.14764321015940773, "std": 0.011705407096411265 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.4845789505375756, "std": 0.023837532285801794 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.09541305568483141, "std": 0.017689412873592346 }, { "family": "CAT", "name": "CatBoost", "mean": 0.11107550631734872, "std": 0.0186922399263044 }, { "family": "GBM", "name": "LightGBM", "mean": 0.10214073276514422, "std": 0.015461760731046686 }, { "family": "XGB", "name": "XGBoost", "mean": 0.10906538820477465, "std": 0.017897874300170417 }, { "family": "RF", "name": "Random forest", "mean": 0.17785348111099128, "std": 0.014184953847596118 }, { "family": "XT", "name": "Extra trees", "mean": 0.17261769910608915, "std": 0.012303760628441027 }, { "family": "LR", "name": "Logistic regression", "mean": 0.14771502216657004, "std": 0.011856068946943289 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.4469137291113536, "std": 0.02542114836452398 } ] } }, { "slug": "superconductor-critical-temperature", "dataset": "superconductivity", "domain": "science", "sourceUrl": "https://www.openml.org/d/46961", "originalSource": "https://doi.org/10.24432/C53P47", "attribution": "Superconductor critical temperature dataset. Original source and curated OpenML task linked below.", "rows": 21263, "features": 81, "target": "critical_temp", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 8.747066645304894, "std": 0.19308099281760388 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 9.259064302998826, "std": 0.20047529326938582, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.5119976576939322, "relativeChange": 5.5296911322681535, "reductionPercent": 5.5296911322681535, "headline": { "value": "5.5%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 8.747066645304894, "std": 0.19308099281760388, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 9.259064302998826, "std": 0.20047529326938582, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 9.340210066731904, "std": 0.19794278790680586, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 9.343398937705716, "std": 0.21305746332276596, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 9.361256920647435, "std": 0.18602701424572304, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 9.525049251965093, "std": 0.18879445186003452, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 9.945711224915819, "std": 0.21639422522086715, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 17.264867439590848, "std": 0.10088195443424454, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 8.747066645304894, "std": 0.19308099281760388 }, { "family": "CAT", "name": "CatBoost", "mean": 9.36614872956954, "std": 0.19113368246031562 }, { "family": "GBM", "name": "LightGBM", "mean": 9.411518728476027, "std": 0.20582155434595883 }, { "family": "XGB", "name": "XGBoost", "mean": 9.449943641994953, "std": 0.17812386154084514 }, { "family": "RF", "name": "Random forest", "mean": 9.626958555586105, "std": 0.19062896840829754 }, { "family": "XT", "name": "Extra trees", "mean": 9.470647144773807, "std": 0.16954824850486788 }, { "family": "LR", "name": "Linear regression", "mean": 17.429718191350485, "std": 0.09597544541071405 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 11.100807625023949, "std": 0.16154010759886842 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 8.747066645304894, "std": 0.19308099281760388 }, { "family": "CAT", "name": "CatBoost", "mean": 9.343398937705716, "std": 0.21305746332276596 }, { "family": "GBM", "name": "LightGBM", "mean": 9.278213551233666, "std": 0.2221992317339248 }, { "family": "XGB", "name": "XGBoost", "mean": 9.353185449778271, "std": 0.20701456823123038 }, { "family": "RF", "name": "Random forest", "mean": 9.621540210725838, "std": 0.19071800016710574 }, { "family": "XT", "name": "Extra trees", "mean": 9.3888854559807, "std": 0.17454990646127094 }, { "family": "LR", "name": "Linear regression", "mean": 17.424116990194847, "std": 0.09423582252984065 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 10.254362644704083, "std": 0.2617928607015063 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 8.747066645304894, "std": 0.19308099281760388 }, { "family": "CAT", "name": "CatBoost", "mean": 9.344062145831632, "std": 0.2025742628541368 }, { "family": "GBM", "name": "LightGBM", "mean": 9.259064302998826, "std": 0.20047529326938582 }, { "family": "XGB", "name": "XGBoost", "mean": 9.340210066731904, "std": 0.19794278790680586 }, { "family": "RF", "name": "Random forest", "mean": 9.525049251965093, "std": 0.18879445186003452 }, { "family": "XT", "name": "Extra trees", "mean": 9.361256920647435, "std": 0.18602701424572304 }, { "family": "LR", "name": "Linear regression", "mean": 17.264867439590848, "std": 0.10088195443424454 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 9.945711224915819, "std": 0.21639422522086715 } ] } }, { "slug": "wine-quality-scores", "dataset": "wine_quality", "domain": "science", "sourceUrl": "https://www.openml.org/d/46964", "originalSource": "https://doi.org/10.24432/C56S3T", "attribution": "Wine quality scores dataset. Original source and curated OpenML task linked below.", "rows": 6497, "features": 12, "target": "median_wine_quality", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.5890740421083238, "std": 0.016552437320803835 }, "strongestConventional": { "family": "XT", "name": "Extra trees", "mean": 0.6006188506147383, "std": 0.020397861870262043, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.011544808506414483, "relativeChange": 1.9221522092751964, "reductionPercent": 1.9221522092751964, "headline": { "value": "1.9%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5890740421083238, "std": 0.016552437320803835, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.6006188506147383, "std": 0.020397861870262043, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.6044300831270726, "std": 0.019632186279036543, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.6065276514357003, "std": 0.018605000170644235, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XGB", "name": "XGBoost", "mean": 0.6097902272758293, "std": 0.019366855940701665, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "RF", "name": "Random forest", "mean": 0.6109064657671713, "std": 0.020584633742650755, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6173406504226109, "std": 0.020946318494322068, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 0.7300065022044335, "std": 0.016232712035079245, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5890740421083238, "std": 0.016552437320803835 }, { "family": "CAT", "name": "CatBoost", "mean": 0.6219291024737887, "std": 0.019835792927199437 }, { "family": "GBM", "name": "LightGBM", "mean": 0.6279094550344679, "std": 0.01876899011599595 }, { "family": "XGB", "name": "XGBoost", "mean": 0.6210696432325575, "std": 0.021136981867659603 }, { "family": "RF", "name": "Random forest", "mean": 0.6201145516501533, "std": 0.02055112140909126 }, { "family": "XT", "name": "Extra trees", "mean": 0.6170974837409126, "std": 0.02043844158256706 }, { "family": "LR", "name": "Linear regression", "mean": 0.7308648427327474, "std": 0.01664722276677455 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6271404359075758, "std": 0.02285352506082054 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5890740421083238, "std": 0.016552437320803835 }, { "family": "CAT", "name": "CatBoost", "mean": 0.6052046706057738, "std": 0.020001269127251947 }, { "family": "GBM", "name": "LightGBM", "mean": 0.6065276514357003, "std": 0.018605000170644235 }, { "family": "XGB", "name": "XGBoost", "mean": 0.6097902272758293, "std": 0.019366855940701665 }, { "family": "RF", "name": "Random forest", "mean": 0.6161290492845292, "std": 0.020753343315897975 }, { "family": "XT", "name": "Extra trees", "mean": 0.6015617646387348, "std": 0.02080527309869046 }, { "family": "LR", "name": "Linear regression", "mean": 0.7308428025821696, "std": 0.016601921151363063 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6269774601580823, "std": 0.021546912240551195 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5890740421083238, "std": 0.016552437320803835 }, { "family": "CAT", "name": "CatBoost", "mean": 0.6044300831270726, "std": 0.019632186279036543 }, { "family": "GBM", "name": "LightGBM", "mean": 0.6080827728162275, "std": 0.018878806254595277 }, { "family": "XGB", "name": "XGBoost", "mean": 0.6103177143378299, "std": 0.019550911891276234 }, { "family": "RF", "name": "Random forest", "mean": 0.6109064657671713, "std": 0.020584633742650755 }, { "family": "XT", "name": "Extra trees", "mean": 0.6006188506147383, "std": 0.020397861870262043 }, { "family": "LR", "name": "Linear regression", "mean": 0.7300065022044335, "std": 0.016232712035079245 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6173406504226109, "std": 0.020946318494322068 } ] } }, { "slug": "california-house-values", "dataset": "houses", "domain": "pricing", "sourceUrl": "https://www.openml.org/d/46934", "originalSource": "https://lib.stat.cmu.edu/datasets/", "attribution": "California house values dataset. Original source and curated OpenML task linked below.", "rows": 20640, "features": 8, "target": "LnMedianHouseValue", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.1873023869010129, "std": 0.0027496576948481863 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.21075659982902972, "std": 0.0022075730081184066, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.023454212928016832, "relativeChange": 11.12857815463117, "reductionPercent": 11.12857815463117, "headline": { "value": "11.1%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1873023869010129, "std": 0.0027496576948481863, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.21075659982902972, "std": 0.0022075730081184066, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.2112009347328461, "std": 0.0023709432708423238, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.21457595532909282, "std": 0.002192983623095862, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.2303505888030724, "std": 0.0017847208518526636, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.23858278365488944, "std": 0.001966352120764074, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.2731759397292591, "std": 0.0023430927859037754, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 0.3234964886056482, "std": 0.0028295702519302956, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1873023869010129, "std": 0.0027496576948481863 }, { "family": "CAT", "name": "CatBoost", "mean": 0.211119853668745, "std": 0.0023059508970110043 }, { "family": "GBM", "name": "LightGBM", "mean": 0.21706200716558047, "std": 0.002374722338720256 }, { "family": "XGB", "name": "XGBoost", "mean": 0.21516284598285612, "std": 0.0027679808507561415 }, { "family": "RF", "name": "Random forest", "mean": 0.2312707431198792, "std": 0.0017809938182150357 }, { "family": "XT", "name": "Extra trees", "mean": 0.24411849268878946, "std": 0.001959858575503949 }, { "family": "LR", "name": "Linear regression", "mean": 0.32527167015747255, "std": 0.0032314122458723844 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.29046984897681666, "std": 0.0017616978477781775 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1873023869010129, "std": 0.0027496576948481863 }, { "family": "CAT", "name": "CatBoost", "mean": 0.2111090536236286, "std": 0.0022155157360119206 }, { "family": "GBM", "name": "LightGBM", "mean": 0.2118051268568428, "std": 0.0021808560300619548 }, { "family": "XGB", "name": "XGBoost", "mean": 0.21498555926204238, "std": 0.0019744773684045656 }, { "family": "RF", "name": "Random forest", "mean": 0.2312707431198792, "std": 0.0017809938182150357 }, { "family": "XT", "name": "Extra trees", "mean": 0.23931996218025803, "std": 0.0020539674947792096 }, { "family": "LR", "name": "Linear regression", "mean": 0.3251361781102939, "std": 0.003241089330799511 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.28193565918149743, "std": 0.002363760162874936 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.1873023869010129, "std": 0.0027496576948481863 }, { "family": "CAT", "name": "CatBoost", "mean": 0.21075659982902972, "std": 0.0022075730081184066 }, { "family": "GBM", "name": "LightGBM", "mean": 0.2112009347328461, "std": 0.0023709432708423238 }, { "family": "XGB", "name": "XGBoost", "mean": 0.21457595532909282, "std": 0.002192983623095862 }, { "family": "RF", "name": "Random forest", "mean": 0.2303505888030724, "std": 0.0017847208518526636 }, { "family": "XT", "name": "Extra trees", "mean": 0.23858278365488944, "std": 0.001966352120764074 }, { "family": "LR", "name": "Linear regression", "mean": 0.3234964886056482, "std": 0.0028295702519302956 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.2731759397292591, "std": 0.0023430927859037754 } ] } }, { "slug": "miami-house-sale-prices", "dataset": "miami_housing", "domain": "pricing", "sourceUrl": "https://www.openml.org/d/46942", "originalSource": "https://www.openml.org/d/43093", "attribution": "Miami house sale prices dataset. Original source and curated OpenML task linked below.", "rows": 13776, "features": 15, "target": "SALE_PRC", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 75142.74669675686, "std": 3935.9000048444937 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 78405.09877796579, "std": 3274.0377638312593, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 3262.3520812089264, "relativeChange": 4.160892763425414, "reductionPercent": 4.160892763425414, "headline": { "value": "4.2%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 75142.74669675686, "std": 3935.9000048444937, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 78405.09877796579, "std": 3274.0377638312593, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 79611.97961544091, "std": 3535.49439203364, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 80415.73677891164, "std": 3566.9777382380466, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 91649.71593472299, "std": 4180.51271248833, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 93023.93611317495, "std": 5002.079232688645, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 101339.68492397876, "std": 5480.791513787419, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 175557.87710860916, "std": 3665.1369779999895, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 75142.74669675686, "std": 3935.9000048444937 }, { "family": "CAT", "name": "CatBoost", "mean": 79760.37601866446, "std": 2856.3609959426103 }, { "family": "GBM", "name": "LightGBM", "mean": 85625.28827909508, "std": 4627.334058571495 }, { "family": "XGB", "name": "XGBoost", "mean": 86503.17738650227, "std": 4465.325390998181 }, { "family": "RF", "name": "Random forest", "mean": 96763.25064912744, "std": 5915.007421455028 }, { "family": "XT", "name": "Extra trees", "mean": 95622.6611594093, "std": 4074.92830089285 }, { "family": "LR", "name": "Linear regression", "mean": 191263.35800779914, "std": 4580.066427144958 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 119572.98503730775, "std": 5645.164418220175 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 75142.74669675686, "std": 3935.9000048444937 }, { "family": "CAT", "name": "CatBoost", "mean": 78423.54319659436, "std": 3423.079370034101 }, { "family": "GBM", "name": "LightGBM", "mean": 81243.28923837801, "std": 4097.403525845781 }, { "family": "XGB", "name": "XGBoost", "mean": 80624.79614599895, "std": 3606.4424486776725 }, { "family": "RF", "name": "Random forest", "mean": 93322.62445418755, "std": 5030.758233988086 }, { "family": "XT", "name": "Extra trees", "mean": 91938.38435395919, "std": 4045.8722042113254 }, { "family": "LR", "name": "Linear regression", "mean": 175565.66174499292, "std": 3664.610286318733 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 104412.25691851646, "std": 5034.512275679166 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 75142.74669675686, "std": 3935.9000048444937 }, { "family": "CAT", "name": "CatBoost", "mean": 78405.09877796579, "std": 3274.0377638312593 }, { "family": "GBM", "name": "LightGBM", "mean": 79611.97961544091, "std": 3535.49439203364 }, { "family": "XGB", "name": "XGBoost", "mean": 80415.73677891164, "std": 3566.9777382380466 }, { "family": "RF", "name": "Random forest", "mean": 93023.93611317495, "std": 5002.079232688645 }, { "family": "XT", "name": "Extra trees", "mean": 91649.71593472299, "std": 4180.51271248833 }, { "family": "LR", "name": "Linear regression", "mean": 175557.87710860916, "std": 3665.1369779999895 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 101339.68492397876, "std": 5480.791513787419 } ] } }, { "slug": "diamond-prices", "dataset": "diamonds", "domain": "pricing", "sourceUrl": "https://www.openml.org/d/46923", "originalSource": "https://github.com/tidyverse/ggplot2/blob/main/data-raw/diamonds.csv", "attribution": "Diamond prices dataset. Original source and curated OpenML task linked below.", "rows": 53940, "features": 9, "target": "price", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 493.6939118975762, "std": 7.52817827103417 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 519.0275244425567, "std": 9.4205144931181, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 25.333612544980497, "relativeChange": 4.880976701994595, "reductionPercent": 4.880976701994595, "headline": { "value": "4.9%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 493.6939118975762, "std": 7.52817827103417, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 519.0275244425567, "std": 9.4205144931181, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 520.3787528193096, "std": 12.596396838038599, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 528.189300547615, "std": 10.911459722351754, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 533.6619961686414, "std": 8.324161399214956, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 547.20403841885, "std": 9.34829582523686, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 668.2531419056012, "std": 14.21191618649388, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 1139.5792124779575, "std": 27.12465041413369, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 493.6939118975762, "std": 7.52817827103417 }, { "family": "CAT", "name": "CatBoost", "mean": 520.3787528193096, "std": 12.596396838038599 }, { "family": "GBM", "name": "LightGBM", "mean": 532.1268732100789, "std": 9.130690008580205 }, { "family": "XGB", "name": "XGBoost", "mean": 538.9907878122222, "std": 10.03430136477953 }, { "family": "RF", "name": "Random forest", "mean": 549.8666550462243, "std": 8.321931970450935 }, { "family": "XT", "name": "Extra trees", "mean": 536.7752858812285, "std": 8.542386748555414 }, { "family": "LR", "name": "Linear regression", "mean": 1652.7663498330962, "std": 179.67416860211196 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 957.3068689771977, "std": 22.10626035832687 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 493.6939118975762, "std": 7.52817827103417 }, { "family": "CAT", "name": "CatBoost", "mean": 520.3787548486412, "std": 12.596395771592395 }, { "family": "GBM", "name": "LightGBM", "mean": 524.8545422072282, "std": 9.671100379456874 }, { "family": "XGB", "name": "XGBoost", "mean": 530.1456047031857, "std": 10.036223406398618 }, { "family": "RF", "name": "Random forest", "mean": 549.8666550462243, "std": 8.321931970450935 }, { "family": "XT", "name": "Extra trees", "mean": 534.6300844077064, "std": 8.119086986908142 }, { "family": "LR", "name": "Linear regression", "mean": 1139.5792124779575, "std": 27.12465041413369 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 706.9205775387761, "std": 15.470685675109191 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 493.6939118975762, "std": 7.52817827103417 }, { "family": "CAT", "name": "CatBoost", "mean": 520.6668095084507, "std": 12.204072770632424 }, { "family": "GBM", "name": "LightGBM", "mean": 519.0275244425567, "std": 9.4205144931181 }, { "family": "XGB", "name": "XGBoost", "mean": 528.189300547615, "std": 10.911459722351754 }, { "family": "RF", "name": "Random forest", "mean": 547.20403841885, "std": 9.34829582523686 }, { "family": "XT", "name": "Extra trees", "mean": 533.6619961686414, "std": 8.324161399214956 }, { "family": "LR", "name": "Linear regression", "mean": 1140.3267128080502, "std": 27.979986850814083 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 668.2531419056012, "std": 14.21191618649388 } ] } }, { "slug": "used-car-asking-prices", "dataset": "Another-Dataset-on-used-Fiat-500", "domain": "pricing", "sourceUrl": "https://www.openml.org/d/46907", "originalSource": "https://www.kaggle.com/datasets/paolocons/another-fiat-500-dataset-1538-rows", "attribution": "Used car prices dataset. Original source and curated OpenML task linked below.", "rows": 1538, "features": 7, "target": "price", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "rmse", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 708.7920141793961, "std": 22.27071776424024 }, "strongestConventional": { "family": "GBM", "name": "LightGBM", "mean": 729.4337460272968, "std": 22.653068805997247, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 20.6417318479007, "relativeChange": 2.8298295712696913, "reductionPercent": 2.8298295712696913, "headline": { "value": "2.8%", "label": "lower prediction error" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 708.7920141793961, "std": 22.27071776424024, "configuration": "default", "configurationLabel": "default" }, { "family": "GBM", "name": "LightGBM", "mean": 729.4337460272968, "std": 22.653068805997247, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 732.686049054546, "std": 22.268704315809394, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 735.3988835642544, "std": 25.337383487125898, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 735.6990726052416, "std": 27.563697248384138, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 737.1118807808091, "std": 22.647900800210287, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Linear regression", "mean": 764.2413474759041, "std": 19.201861988045582, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 782.1517489018757, "std": 27.742165701570357, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 708.7920141793961, "std": 22.27071776424024 }, { "family": "CAT", "name": "CatBoost", "mean": 737.8291301136479, "std": 21.93523178164752 }, { "family": "GBM", "name": "LightGBM", "mean": 746.022407145816, "std": 22.429954275268084 }, { "family": "XGB", "name": "XGBoost", "mean": 754.6256411108839, "std": 22.9712365755726 }, { "family": "RF", "name": "Random forest", "mean": 750.8037703405031, "std": 28.44075342142288 }, { "family": "XT", "name": "Extra trees", "mean": 739.9746632586769, "std": 29.219484458938815 }, { "family": "LR", "name": "Linear regression", "mean": 793.8036800222135, "std": 25.388665175537565 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 823.6719634882018, "std": 28.927507428747568 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 708.7920141793961, "std": 22.27071776424024 }, { "family": "CAT", "name": "CatBoost", "mean": 735.7942177425003, "std": 22.06297429764085 }, { "family": "GBM", "name": "LightGBM", "mean": 740.4029951703247, "std": 24.585554946078158 }, { "family": "XGB", "name": "XGBoost", "mean": 741.3663713291128, "std": 22.17355218879468 }, { "family": "RF", "name": "Random forest", "mean": 736.5321814510237, "std": 24.754882646417098 }, { "family": "XT", "name": "Extra trees", "mean": 737.1967041448909, "std": 27.14415169540055 }, { "family": "LR", "name": "Linear regression", "mean": 764.2413474759041, "std": 19.201861988045582 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 801.4697586975988, "std": 29.50572826398178 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 708.7920141793961, "std": 22.27071776424024 }, { "family": "CAT", "name": "CatBoost", "mean": 732.686049054546, "std": 22.268704315809394 }, { "family": "GBM", "name": "LightGBM", "mean": 729.4337460272968, "std": 22.653068805997247 }, { "family": "XGB", "name": "XGBoost", "mean": 737.1118807808091, "std": 22.647900800210287 }, { "family": "RF", "name": "Random forest", "mean": 735.3988835642544, "std": 25.337383487125898 }, { "family": "XT", "name": "Extra trees", "mean": 735.6990726052416, "std": 27.563697248384138 }, { "family": "LR", "name": "Linear regression", "mean": 764.3661936354255, "std": 19.303329517596282 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 782.1517489018757, "std": 27.742165701570357 } ] } }, { "slug": "student-academic-outcomes", "dataset": "students_dropout_and_academic_success", "domain": "people", "sourceUrl": "https://www.openml.org/d/46960", "originalSource": "https://doi.org/10.24432/C5MC89", "attribution": "Student academic outcomes dataset. Original source and curated OpenML task linked below.", "rows": 4424, "features": 36, "target": "AcademicOutcome", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.5270925230450101, "std": 0.013822297715181403 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.5406986698525379, "std": 0.015794692123269283, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.013606146807527808, "relativeChange": 2.516401013384876, "reductionPercent": 2.516401013384876, "headline": { "value": "2.5%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5270925230450101, "std": 0.013822297715181403, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.5406986698525379, "std": 0.015794692123269283, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.5420396854071325, "std": 0.015444482460426368, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.5447693716091886, "std": 0.01519605146726034, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.5607898765140109, "std": 0.01292341045163644, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.5661014004826983, "std": 0.013114424691693802, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.5737223837519447, "std": 0.012817470287235557, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6634034050835503, "std": 0.016615892080955853, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5270925230450101, "std": 0.013822297715181403 }, { "family": "CAT", "name": "CatBoost", "mean": 0.5516800416987323, "std": 0.017259116522406245 }, { "family": "GBM", "name": "LightGBM", "mean": 0.5547765029501902, "std": 0.014693642655353919 }, { "family": "XGB", "name": "XGBoost", "mean": 0.5540833506273715, "std": 0.01645588791759683 }, { "family": "RF", "name": "Random forest", "mean": 0.5840633992542706, "std": 0.010725125202298302 }, { "family": "XT", "name": "Extra trees", "mean": 0.5904834827923092, "std": 0.011868188515113105 }, { "family": "LR", "name": "Logistic regression", "mean": 0.5710187342144759, "std": 0.01657862988973332 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8285651020916712, "std": 0.047365951515228676 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5270925230450101, "std": 0.013822297715181403 }, { "family": "CAT", "name": "CatBoost", "mean": 0.5419020245145794, "std": 0.01637207439678153 }, { "family": "GBM", "name": "LightGBM", "mean": 0.5430489325858445, "std": 0.016123847058864018 }, { "family": "XGB", "name": "XGBoost", "mean": 0.5447693716091886, "std": 0.01519605146726034 }, { "family": "RF", "name": "Random forest", "mean": 0.5763839182370801, "std": 0.013714048962766316 }, { "family": "XT", "name": "Extra trees", "mean": 0.569950115083739, "std": 0.011557105246643688 }, { "family": "LR", "name": "Logistic regression", "mean": 0.5624600052833557, "std": 0.012987941119201922 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7053685784339905, "std": 0.017782286864124388 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.5270925230450101, "std": 0.013822297715181403 }, { "family": "CAT", "name": "CatBoost", "mean": 0.5406986698525379, "std": 0.015794692123269283 }, { "family": "GBM", "name": "LightGBM", "mean": 0.5420396854071325, "std": 0.015444482460426368 }, { "family": "XGB", "name": "XGBoost", "mean": 0.5455393390692577, "std": 0.014195834435874638 }, { "family": "RF", "name": "Random forest", "mean": 0.5737223837519447, "std": 0.012817470287235557 }, { "family": "XT", "name": "Extra trees", "mean": 0.5661014004826983, "std": 0.013114424691693802 }, { "family": "LR", "name": "Logistic regression", "mean": 0.5607898765140109, "std": 0.01292341045163644 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.6634034050835503, "std": 0.016615892080955853 } ] } }, { "slug": "job-change-interest", "dataset": "HR_Analytics_Job_Change_of_Data_Scientists", "domain": "people", "sourceUrl": "https://www.openml.org/d/46935", "originalSource": "https://www.kaggle.com/datasets/arashnic/hr-analytics-job-change-of-data-scientists", "attribution": "Job-change interest dataset. Original source and curated OpenML task linked below.", "rows": 19158, "features": 12, "target": "LookingForJobChange", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8077804510631937, "std": 0.0061026693775795915 }, "strongestConventional": { "family": "XGB", "name": "XGBoost", "mean": 0.8047147026088645, "std": 0.005581820579717878, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.0030657484543292757, "relativeChange": 0.3809733368099524, "reductionPercent": null, "headline": { "value": "0.31 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8077804510631937, "std": 0.0061026693775795915, "configuration": "default", "configurationLabel": "default" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8047147026088645, "std": 0.005581820579717878, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.80430478160499, "std": 0.006109191355197938, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.804277925013775, "std": 0.005548076605707938, "configuration": "default", "configurationLabel": "default" }, { "family": "RF", "name": "Random forest", "mean": 0.8024152781836421, "std": 0.006296581920658754, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XT", "name": "Extra trees", "mean": 0.8006440243829275, "std": 0.006142384225002379, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7979969566436768, "std": 0.006560428207666603, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.7975485860165962, "std": 0.0049813192647842645, "configuration": "tuned", "configurationLabel": "tuned" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8077804510631937, "std": 0.0061026693775795915 }, { "family": "CAT", "name": "CatBoost", "mean": 0.804277925013775, "std": 0.005548076605707938 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8016858412572965, "std": 0.00653174174399061 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8046757574255582, "std": 0.006134459599871498 }, { "family": "RF", "name": "Random forest", "mean": 0.7887762651488633, "std": 0.005816378870582299 }, { "family": "XT", "name": "Extra trees", "mean": 0.7877459280330001, "std": 0.0063742155978797595 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7960392634950783, "std": 0.005755068295078522 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7454610863049207, "std": 0.007278680087112176 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8077804510631937, "std": 0.0061026693775795915 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8038689370907411, "std": 0.005830995820725282 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8032348661338181, "std": 0.006543411650688137 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8034407684284769, "std": 0.0054451745651311525 }, { "family": "RF", "name": "Random forest", "mean": 0.8024152781836421, "std": 0.006296581920658754 }, { "family": "XT", "name": "Extra trees", "mean": 0.8006440243829275, "std": 0.006142384225002379 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7975485860165962, "std": 0.0049813192647842645 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7888560024244397, "std": 0.007464028640065649 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8077804510631937, "std": 0.0061026693775795915 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8037260710498185, "std": 0.006087058381327297 }, { "family": "GBM", "name": "LightGBM", "mean": 0.80430478160499, "std": 0.006109191355197938 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8047147026088645, "std": 0.005581820579717878 }, { "family": "RF", "name": "Random forest", "mean": 0.8017881497497985, "std": 0.006204848308859166 }, { "family": "XT", "name": "Extra trees", "mean": 0.8005357799966721, "std": 0.006518550018026348 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7974100311167756, "std": 0.0051076884817309424 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7979969566436768, "std": 0.006560428207666603 } ] } }, { "slug": "employee-resource-access", "dataset": "Amazon_employee_access", "domain": "people", "sourceUrl": "https://www.openml.org/d/46905", "originalSource": "https://www.kaggle.com/c/amazon-employee-access-challenge", "attribution": "Employee resource access dataset. Original source and curated OpenML task linked below.", "rows": 32769, "features": 9, "target": "ResourceApproved", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.8590808793605723, "std": 0.005064326475846699 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.8823984403149965, "std": 0.007031811731355333, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": -0.023317560954424166, "relativeChange": -2.6425206447668153, "reductionPercent": null, "headline": { "value": "2.33 pp", "label": "lower ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8590808793605723, "std": 0.005064326475846699, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.8823984403149965, "std": 0.007031811731355333, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.8617225206753194, "std": 0.008287167390240213, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.8581184996255519, "std": 0.008767092134621257, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8520437831919301, "std": 0.006284969752225189, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.851341186582838, "std": 0.008022124029215644, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.8488901349759778, "std": 0.00485341406202714, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.8460162176638442, "std": 0.005201774902506023, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8590808793605723, "std": 0.005064326475846699 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8817652194738004, "std": 0.008217410530789244 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8426989169328093, "std": 0.008640245159407657 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8343558830039851, "std": 0.0068506255325724635 }, { "family": "RF", "name": "Random forest", "mean": 0.8391896861548056, "std": 0.004681694875066572 }, { "family": "XT", "name": "Extra trees", "mean": 0.8381523704972724, "std": 0.005228729776614386 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8482367279837402, "std": 0.00871259311531486 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7502598891370973, "std": 0.005645353353529096 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8590808793605723, "std": 0.005064326475846699 }, { "family": "CAT", "name": "CatBoost", "mean": 0.882391128293332, "std": 0.007742527616616218 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8500259161802398, "std": 0.007337544545516551 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8585417702598661, "std": 0.008343024806965107 }, { "family": "RF", "name": "Random forest", "mean": 0.8407529248128113, "std": 0.00528444468296854 }, { "family": "XT", "name": "Extra trees", "mean": 0.8431027544028695, "std": 0.005227493322887643 }, { "family": "LR", "name": "Logistic regression", "mean": 0.8502713234508662, "std": 0.008276914948402561 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8170788242848567, "std": 0.006035372611457584 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.8590808793605723, "std": 0.005064326475846699 }, { "family": "CAT", "name": "CatBoost", "mean": 0.8823984403149965, "std": 0.007031811731355333 }, { "family": "GBM", "name": "LightGBM", "mean": 0.8581184996255519, "std": 0.008767092134621257 }, { "family": "XGB", "name": "XGBoost", "mean": 0.8617225206753194, "std": 0.008287167390240213 }, { "family": "RF", "name": "Random forest", "mean": 0.8488901349759778, "std": 0.00485341406202714 }, { "family": "XT", "name": "Extra trees", "mean": 0.8460162176638442, "std": 0.005201774902506023 }, { "family": "LR", "name": "Logistic regression", "mean": 0.851341186582838, "std": 0.008022124029215644 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.8520437831919301, "std": 0.006284969752225189 } ] } }, { "slug": "android-malware-detection", "dataset": "NATICUSdroid", "domain": "software", "sourceUrl": "https://www.openml.org/d/46969", "originalSource": "https://doi.org/10.24432/C5FS64", "attribution": "Android malware detection dataset. Original source and curated OpenML task linked below.", "rows": 7491, "features": 86, "target": "Malware", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.9880832720375698, "std": 0.0013380326062006178 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.9860675271576199, "std": 0.001704565836883168, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.0020157448799499322, "relativeChange": 0.20442260032235313, "reductionPercent": null, "headline": { "value": "0.20 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9880832720375698, "std": 0.0013380326062006178, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.9860675271576199, "std": 0.001704565836883168, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.9859906836039676, "std": 0.0017462912176442254, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "XGB", "name": "XGBoost", "mean": 0.9854693068476286, "std": 0.0018444125450108022, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.9825410052723852, "std": 0.002313741722319506, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "RF", "name": "Random forest", "mean": 0.981033085429137, "std": 0.0025300822448104145, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.9809807720000029, "std": 0.0017450789724895895, "configuration": "default", "configurationLabel": "default" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9800410923673762, "std": 0.0026805773155308826, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9880832720375698, "std": 0.0013380326062006178 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9859471238976419, "std": 0.0017846036198199706 }, { "family": "GBM", "name": "LightGBM", "mean": 0.984676348265888, "std": 0.002043213903282036 }, { "family": "XGB", "name": "XGBoost", "mean": 0.984528017005435, "std": 0.0019940491819562985 }, { "family": "RF", "name": "Random forest", "mean": 0.9773256498423095, "std": 0.002161657821781208 }, { "family": "XT", "name": "Extra trees", "mean": 0.9787417476138104, "std": 0.0022615098448852296 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9809807720000029, "std": 0.0017450789724895895 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9478965198012508, "std": 0.004017364976667988 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9880832720375698, "std": 0.0013380326062006178 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9859857472393753, "std": 0.0018708709199991187 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9859906836039676, "std": 0.0017462912176442254 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9854462254214311, "std": 0.001946369878475915 }, { "family": "RF", "name": "Random forest", "mean": 0.9808022487800179, "std": 0.0025193167973904676 }, { "family": "XT", "name": "Extra trees", "mean": 0.9825410052723852, "std": 0.002313741722319506 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9808975902764006, "std": 0.0018211246667571511 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9775254940430441, "std": 0.0028705967070109173 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.9880832720375698, "std": 0.0013380326062006178 }, { "family": "CAT", "name": "CatBoost", "mean": 0.9860675271576199, "std": 0.001704565836883168 }, { "family": "GBM", "name": "LightGBM", "mean": 0.9859616744741803, "std": 0.0017589239764915373 }, { "family": "XGB", "name": "XGBoost", "mean": 0.9854693068476286, "std": 0.0018444125450108022 }, { "family": "RF", "name": "Random forest", "mean": 0.981033085429137, "std": 0.0025300822448104145 }, { "family": "XT", "name": "Extra trees", "mean": 0.9825168088899514, "std": 0.0022537686996630937 }, { "family": "LR", "name": "Logistic regression", "mean": 0.9809029937180245, "std": 0.0018130367371540469 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9800410923673762, "std": 0.0026805773155308826 } ] } }, { "slug": "phishing-website-classification", "dataset": "website_phishing", "domain": "software", "sourceUrl": "https://www.openml.org/d/46963", "originalSource": "https://doi.org/10.24432/C5B301", "attribution": "Phishing website classification dataset. Original source and curated OpenML task linked below.", "rows": 1353, "features": 9, "target": "WebsiteType", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 30, "metric": "log_loss", "direction": "lower", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.21630147198836008, "std": 0.022175641659733215 }, "strongestConventional": { "family": "CAT", "name": "CatBoost", "mean": 0.23818849722650315, "std": 0.02147399032969334, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.021887025238143065, "relativeChange": 9.188951394797963, "reductionPercent": 9.188951394797963, "headline": { "value": "9.2%", "label": "lower prediction log loss" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.21630147198836008, "std": 0.022175641659733215, "configuration": "default", "configurationLabel": "default" }, { "family": "CAT", "name": "CatBoost", "mean": 0.23818849722650315, "std": 0.02147399032969334, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.2465666792726732, "std": 0.020756504065111283, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XT", "name": "Extra trees", "mean": 0.24945628354577415, "std": 0.018564346556400144, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.2506516201082565, "std": 0.022557635489007917, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.2571798420581598, "std": 0.019226673163866708, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.29869215041399, "std": 0.033293875913097314, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "LR", "name": "Logistic regression", "mean": 0.3578306754430135, "std": 0.02176027888554407, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.21630147198836008, "std": 0.022175641659733215 }, { "family": "CAT", "name": "CatBoost", "mean": 0.2526404859644089, "std": 0.022727802512161322 }, { "family": "GBM", "name": "LightGBM", "mean": 0.25476617643597765, "std": 0.020776653389400306 }, { "family": "XGB", "name": "XGBoost", "mean": 0.2598222359953889, "std": 0.027201810253161287 }, { "family": "RF", "name": "Random forest", "mean": 0.3115973074387953, "std": 0.03695141291844917 }, { "family": "XT", "name": "Extra trees", "mean": 0.29368306314314685, "std": 0.028756951882806154 }, { "family": "LR", "name": "Logistic regression", "mean": 0.35967066215772814, "std": 0.02104781330361281 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.9379683761547418, "std": 0.14217524483474192 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.21630147198836008, "std": 0.022175641659733215 }, { "family": "CAT", "name": "CatBoost", "mean": 0.2401776001366334, "std": 0.023398198147447622 }, { "family": "GBM", "name": "LightGBM", "mean": 0.24872216925022866, "std": 0.021368642226787072 }, { "family": "XGB", "name": "XGBoost", "mean": 0.2513634253447257, "std": 0.021777875511161 }, { "family": "RF", "name": "Random forest", "mean": 0.26214389156534074, "std": 0.018984819231026878 }, { "family": "XT", "name": "Extra trees", "mean": 0.2576661698661639, "std": 0.022370178953717564 }, { "family": "LR", "name": "Logistic regression", "mean": 0.35899143616358437, "std": 0.022645421524111406 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.38491723239421843, "std": 0.04848703852398526 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.21630147198836008, "std": 0.022175641659733215 }, { "family": "CAT", "name": "CatBoost", "mean": 0.23818849722650315, "std": 0.02147399032969334 }, { "family": "GBM", "name": "LightGBM", "mean": 0.2465666792726732, "std": 0.020756504065111283 }, { "family": "XGB", "name": "XGBoost", "mean": 0.2506516201082565, "std": 0.022557635489007917 }, { "family": "RF", "name": "Random forest", "mean": 0.2571798420581598, "std": 0.019226673163866708 }, { "family": "XT", "name": "Extra trees", "mean": 0.24945628354577415, "std": 0.018564346556400144 }, { "family": "LR", "name": "Logistic regression", "mean": 0.3578306754430135, "std": 0.02176027888554407 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.29869215041399, "std": 0.033293875913097314 } ] } }, { "slug": "software-defect-detection", "dataset": "jm1", "domain": "software", "sourceUrl": "https://www.openml.org/d/46979", "originalSource": "https://www.openml.org/d/1053", "attribution": "Software defect detection dataset. Original source and curated OpenML task linked below.", "rows": 10885, "features": 21, "target": "defects", "targetUnit": "Recorded target scale; physical unit unspecified", "splits": 9, "metric": "roc_auc", "direction": "higher", "causilo": { "family": "CAUSILO", "name": "Causilo", "mean": 0.7798655841596941, "std": 0.00518766035109635 }, "strongestConventional": { "family": "XT", "name": "Extra trees", "mean": 0.765609783836937, "std": 0.006121510600153702, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, "signedDifference": 0.014255800322757084, "relativeChange": 1.8620190890603023, "reductionPercent": null, "headline": { "value": "1.43 pp", "label": "higher ROC AUC" }, "comparisons": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7798655841596941, "std": 0.00518766035109635, "configuration": "default", "configurationLabel": "default" }, { "family": "XT", "name": "Extra trees", "mean": 0.765609783836937, "std": 0.006121510600153702, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "RF", "name": "Random forest", "mean": 0.7608170015156192, "std": 0.007205771596399707, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7605246419402582, "std": 0.006640798811388552, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "GBM", "name": "LightGBM", "mean": 0.7528087217853, "std": 0.006226596477473933, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "XGB", "name": "XGBoost", "mean": 0.7517537105837803, "std": 0.006324186876581681, "configuration": "tuned_ensemble", "configurationLabel": "tuned ensemble" }, { "family": "CAT", "name": "CatBoost", "mean": 0.7507897908968203, "std": 0.004516856566510023, "configuration": "tuned", "configurationLabel": "tuned" }, { "family": "LR", "name": "Logistic regression", "mean": 0.723862982173639, "std": 0.006487100054585408, "configuration": "default", "configurationLabel": "default" } ], "configurations": { "default": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7798655841596941, "std": 0.00518766035109635 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7446784278395393, "std": 0.005140600015554067 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7483258872375026, "std": 0.0062700586664629875 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7480991414783873, "std": 0.007077101346851021 }, { "family": "RF", "name": "Random forest", "mean": 0.7516002854572773, "std": 0.00803735476082172 }, { "family": "XT", "name": "Extra trees", "mean": 0.7582032094583616, "std": 0.006941770835583309 }, { "family": "LR", "name": "Logistic regression", "mean": 0.723862982173639, "std": 0.006487100054585408 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.739995975400567, "std": 0.006626380853002185 } ], "tuned": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7798655841596941, "std": 0.00518766035109635 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7507897908968203, "std": 0.004516856566510023 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7512880986569193, "std": 0.006284201759680694 }, { "family": "XGB", "name": "XGBoost", "mean": 0.749250581009792, "std": 0.006639629296522123 }, { "family": "RF", "name": "Random forest", "mean": 0.7515591250903938, "std": 0.00790661080633564 }, { "family": "XT", "name": "Extra trees", "mean": 0.7598637943523832, "std": 0.007081240813668755 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7234824599289742, "std": 0.006180928480196603 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7501698432798176, "std": 0.006981174058268589 } ], "tuned_ensemble": [ { "family": "CAUSILO", "name": "Causilo", "mean": 0.7798655841596941, "std": 0.00518766035109635 }, { "family": "CAT", "name": "CatBoost", "mean": 0.7492429469989673, "std": 0.004959248115840798 }, { "family": "GBM", "name": "LightGBM", "mean": 0.7528087217853, "std": 0.006226596477473933 }, { "family": "XGB", "name": "XGBoost", "mean": 0.7517537105837803, "std": 0.006324186876581681 }, { "family": "RF", "name": "Random forest", "mean": 0.7608170015156192, "std": 0.007205771596399707 }, { "family": "XT", "name": "Extra trees", "mean": 0.765609783836937, "std": 0.006121510600153702 }, { "family": "LR", "name": "Logistic regression", "mean": 0.7235608614163189, "std": 0.00626745527643065 }, { "family": "KNN", "name": "K-nearest neighbors", "mean": 0.7605246419402582, "std": 0.006640798811388552 } ] } } ] }