Table 4 Hyperparameters configuration for machine learning models.

LR

Penalty/regularization

None (Ordinary least square)

Fit intercept

True

Normalize

False

DTR

Criterion

Squared error

Maximum depth

6

Minimum samples split

4

Minimum samples leaf

2

Random state

42

RF

Number of trees

100

Maximum depth

10

Minimum samples split

2

Minimum samples leaf

1

Bootstrap

True

Random state

42

GBM

Learning rate

0.1

Number of estimators

100

Maximum depth

3

Subsample

1

Loss function

Squared error

Random state

42

XGBoost

Learning rate

0.1

Number of estimators

100

Maximum depth

5

Subsample

0.8

Col sample_ by tree

0.8

Gamma

0

Random state

42

SVR

Kernel

Radial basis function (RBF)

C (Regularization parameter)

1

Gamma

‘Scale’

Epsilon

0.1

GPR

Kernel

RBF + White Kernel

Alpha (noise level)

1e−10

Normalizer

True

KR

Kernel

RBF

Alpha

1

Gamma

0.1

MLP

Hidden Layer Sizes

(10,)

Activation Function

ReLU

Solver

Adam

Learning Rate

‘Constant’

Learning Rate Init

0.001

Maximum Iterations

1000

Random State

42