Table 3 Hyperparameters for grid search
Classifier | Hyperparameters for tuning | Options |
|---|---|---|
KNN | Number of neighbors | 1, 3, 5, 7, 9, 11, 13 |
SVM | Regularization parameter | 1, 2, 5, 7, 10, 50, 100, 200, 400 |
| Â | Kernel coefficient | 0.001, 0.01, 0.05, 0.1, 1 |
AdaBoost | Number of base estimators | 10, 30, 60, 100, 200, 400 |
| Â | Max depth of base estimators | 1, 2, 3, 4, 5, 10, 15, 30, 60 |
RF | Number of estimators | 10, 30, 60, 100, 200, 400 |
| Â | Max depth of estimators | 1, 2, 3, 4, 5, 10, 15, 30, 60 |
LGBM | Number of estimators | 1, 2, 3, 4, 5, 10, 15, 30, 60 |
| Â | Max depth of estimators | 10, 30, 60, 100, 200, 400 |
XGB | Number of estimators | 1, 2, 3, 4, 5, 10, 15, 30, 60 |
| Â | Max depth of estimators | 10, 30, 60, 100, 200, 400 |
LR | Regularization parameter | 0.001, 0.01, 0.1, 1, 10, 100, 1000 |
DT | Max depth | 2, 3, 4, 5, 10, 50 |
|  | Criterion | ‘gini’, ‘entropy’, ‘log_loss’ |
|  | Splitter | ‘best’, ‘random’ |
GP | Population size | 100, 300, 500, 1000, 3000 |
| Â | Number of generations | 20, 50, 100, 200 |
|  | Initial depth | (2–2), (2–6) |
| Â | Tournament size | 2, 7, 20 |
GE | Population size | 100, 300, 500, 1000, 3000 |
| Â | Number of generations | 50, 100, 200 |