TABLE 1.

Hyperparameters explored using grid search cross-validation for the different regressors examined in the study.

Regressor	Hyperparameters	Values
Ridge regression	Polynomial degree	1, 2, 3
	Regularization penalty	10–4, 10–3, 10–2, 10–1, 10, 102
Random forest	Number of estimators	100, 200, 300
	Maximum number of features	5, 6, 7
	Maximum depth	6, 7
Multi-layer perceptron	Number of hidden layers	1, 2
	Number of neurons per hidden layer	3, 4
	Activation function	relu, tanh
	Regularization penalty	10–3, 10–2, 10–1
Support vector regression	Kernel type	Linear, poly, RBF, sigmoid
	Regularization parameter	2–5, 2–3, 2–1, 2, 23
	Epsilon	10–3, 10–2, 10–1

RBF stands for Radial basis function.