Table 2.

Optimal hyperparameters.

Model name	Optimal hyperparameters
Random forest regressor	‘n estimators’: [100] ‘max features’: [‘sqrt’, ‘log2’] ‘max depth’: [20] ‘min samples split’: [2] ‘min samples leaf’: [1] ‘bootstrap’: [False]
XGBoost	’learning rate’: [0.1] ‘n estimators’: [500] ‘max depth’: [3] ‘subsample’: [1] ‘colsample bytree’: [1] ‘min child weight’: [1] ‘gamma’: [0]
Support Vector Regressor	’C′: [1000] ‘gamma’: [0.1, 1] ‘kernel’: [‘rbf’] ‘epsilon’: [0.1] ‘shrinking’: [True]
GAN	‘latent dim’: [10] ‘epochs’: [1000] ‘batch size’: [16] ‘learning rate’: [0.0002] ‘beta 1’: [0.5, 0.9] ‘beta 2’: [0.999, 0.9999] ‘activation function’: [‘LeakyReLU’, ‘ReLU’, ‘Sigmoid’]