Table 2 Extreme Gradient Boosting regression modeling hyperparameters from the grid search.

n_estimators

Number of iterations in training

10–1000

56

Eta

Model learning rate

0.02–0.05

0.03

max_depth

Maximum depth of the tree

4–8

4

Gamma

Minimal loss reduction required to perform an additional partition on a leaf node of the tree

0

0

colsample_bytree

The last parameter that we need to config

0.5–0.9

0.5

min_child_weight

Sum of sample weight of the smallest leaf nodes to prevent overfitting

1–2

1

subsample

Sampling rate of all training samples

1–3

1