Table 7.

Hyperparameter tuning attribution.

Model	Parameters
	Grid Parameters	Grid Values	Tuned Values
Random Forest Regressor	n_estimators max_depth min_samples_split min_samples_leaf	: [10,25,50,75,100] : [10,25,50,75,100] : [2,4,6,8,10] : [1,2,3,4,5]	{n_estimators: 100}, {max_depth: 25}, {min_samples_split: 2}, {min_samples_leaf: 1}
CatBoost Regressor	depth learning_rate iterations	: [10,25,50] : [0.1,0.5,1] : [50,100,250]	{depth: 10}, {learning_rate: 0.1}, {iterations: 250}
Extreme Gradient Boosting (XGB) Regressor	n_estimators max_depth learning_rate	: [50,100,150,200,250] : [5,10,25,50] : [0,0.5,1]	{n_estimators: 250}, {max_depth: 7}, {learning_rate: 0.01}
Light Gradient Boosting Machine (LightGBM) Regressor)	n_estimators max_depth learning_rate	: [50,75,100] : [10,50,100] : [0.05,0.1,0.5,1]	{n_estimators: 100}, {max_depth: 10}, {learning_rate: 0.5}