Table 5.

Hyper-parameters and values tested during tuning for the regression.

Algorithm	Parameter	Values
LASSO	Alpha	1.0, 0.75, 0.5, 0.25
EN	Alpha	1.0, 0.75, 0.5, 0.25
KNN	N Neighbors	3, 7, 11, 15, 21
	Leaf Size	1, 2, 3, 5
	Weights	uniform, distance
	Algorithm	auto, ball tree, kd tree, brute
RF	Min Samples Leaf	1, 3, 5
	Min Samples Split	2, 4, 6
	Max Depth	3, 5, 8
	Max Features	log2, sqrt
	Criterion	mse,mae
	Bootstrap	true, false
	Number of Estimators	50, 100, 200, 500
Gb	Learning Rate	0.01, 0.05, 0.1, 0.2
	Min Samples Leaf	1, 3, 5
	Min Samples Split	2, 4, 6
	Max Depth	3, 5, 8
	Max Features	log2, sqrt
	Criterion	friedman mse, mae
	Subsample	0.5, 0.75, 1
	Number of Estimators	50, 100, 200, 500
ET	Min Samples Leaf	1, 3, 5
	Min Samples Split	2, 4, 6
	Max Depth	3, 5, 8
	Max Features	log2, sqrt
	Criterion	mse,mae
	Number of Estimators	50, 100, 200, 500