Table 6 Control parameters employed in development and application of soft computing techniques.
 | Parameters | Value |
---|---|---|
GradientBoosting | n-Estimators | 120 |
Max depth | 5 | |
Learning rate | 0.10 | |
Subsample | 1 | |
Alpha | 0.90 | |
Min samples split | 2 | |
XGBoost | n-Estimators | 94 |
Max depth | 9 | |
Learning rate | 0.08 | |
Subsample | 0.75 | |
Gamma | 0 | |
Col sample by tree | 1 | |
CatBoost | Depth | 7 |
Learning rate | 0.07 | |
Iterations | 300 | |
Best model min trees | 1 | |
Bootstrap type | MVS | |
Leaf estimation method | Newton |