Table A2.
The list of candidate parameters and parameters tuning results for finding the optimal parameter set in XGBoost.
| List of Candidate Hyperparameters | |||||
| n_estimators | Colsample_bytree | Learning_rate | Max_depth | Subsample | |
| {500, 1000, 1500, 2000, 2500, 3000} | {0.2, 0.4, 0.6, 0.8, 1.0} | {0.01, 0.03, 0.05, 0.07, 0.09} | {5, 6, 7, 8, 9} | {0.2, 0.4, 0.6, 0.8, 1.0} | |
| Hyperparameters Tuning Results (top 6) | |||||
| n_estimators | Colsample_bytree | Learning_rate | Max_depth | Subsample | Best Score |
| 3000 | 1.0 | 0.03 | 9 | 0.4 | 0.998009 |
| 2500 | 1.0 | 0.03 | 9 | 0.4 | 0.997989 |
| 3000 | 1.0 | 0.03 | 8 | 0.4 | 0.997984 |
| 2000 | 1.0 | 0.03 | 9 | 0.4 | 0.997951 |
| 2500 | 1.0 | 0.03 | 8 | 0.4 | 0.997945 |
| 3000 | 1.0 | 0.05 | 8 | 0.4 | 0.997924 |