Table 2.

Hyperparameter selection

Prediction model	Hyperparameter	Parameter selection	Best hyperparameter used
LR	dual	[True, False]	False
	max_iter	[100,110,120,130,140]	100
	C	[1,1.5,2,2.5]	2
SVR	kernel	rbf	rbf
	C	[0.1, 1, 100, 1000]	100
	Gamma	[0.0001, 0.001,0.01 0.005, 0.1, 1, 3, 5]	0.1
	Epsilon	[0.0001, 0.001, 0.01, 0.05, 0.1, 0.5, 1, 5, 10]	0.0001
RFR	bootstrap	[True, False]	True
	max_depth	[10, 20, 30, 40, 50, 60, 70, 80, 90, 100, None]	70
	max_features	[‘auto’, ‘sqrt’]	auto
	min_samples_leaf	[1, 2, 4]	4
	min_samples_split	[2, 5, 10]	10
	n_estimators	[100, 200, 400, 600, 800, 1000, 1200, 1400, 1600, 1800, 2000]	400
LSTM	neurons	[1–5]	1
	batches	[1, 2, 4]	4
	epochs	[500, 1000, 2000, 4000, 6000]	1000