Table 1.

Model names and hyperparameter tuning settings.

Model name	Hyperparameters for model
Random forest regressor	‘n estimators’: [100, 300, 500] ‘max features’: [‘auto’, ‘sqrt’, ‘log2’] ‘max depth’: [None, 10, 20, 30] ‘min samples split’: [2, 5, 10] ‘min samples leaf’: [1, 2, 4] ‘bootstrap’: [True, False]
XGBoost	‘learning rate’: [1, 0.1, 0.01, 0.001] ‘n estimators’: [100, 500, 1,000] ‘max depth’: [3, 5, 8] ‘subsample’: [0.7, 1] ‘colsample bytree’: [0.7, 1] ‘min child weight’: [1, 5, 10] ‘gamma’: [0, 0.1, 0.2]
Support vector regressor	‘C′: [1, 10, 100, 1,000] ‘gamma’: [1, 0.1, 0.01, 0.001, 0.0001] ‘kernel’: [‘rbf’] ‘epsilon’: [0.1, 0.01, 0.001] ‘shrinking’: [True, False]
GAN	‘latent dim’: [5, 10, 20] ‘epochs’: [200, 500, 1,000] ‘batch size’: [16, 32, 64] ‘learning rate’: [0.0002, 0.0001, 0.00005] ‘beta 1’: [0.5, 0.9] ‘beta 2’: [0.999, 0.9999] ‘activation function’: [‘LeakyReLU’, ‘ReLU’, ‘Sigmoid’]