Table 2 Model hyperparameters selected for models trained on a subset of features selected by a given method
From: Evaluating the risk of endometriosis based on patients’ self-assessment questionnaires
Method | colsample bytree | learning rate | max bin | max depth | num leaves | reg alpha | reg lambda | subsample | subsample freq |
|---|---|---|---|---|---|---|---|---|---|
Boruta | 0.50 | 0.10 | 39 | 3 | 31 | 0.20 | 0.20 | 0.30 | 51 |
Experts’ decisions | 0.29 | 0.03 | 46 | 6 | 20 | 0.05 | 0.07 | 0.76 | 48 |
Recursive selection | 0.28 | 0.05 | 53 | 5 | 9 | 0.10 | 0.07 | 0.75 | 47 |