Table 3.

Key parameter settings for each ensemble learning model.

Model	Parameter name	Parameter settings
LightGBM	n_jobs	-1
	n_estimators	600
	learning_rate	0.01
	max_depth	5
	num_leaves	32
	colsample_bytree	0.51
	subsample	0.6
CatBoost	iterations	5000
	learning_rate	0.01
	l2_leaf_reg	3
	bagging_temperature	1
	subsample	0.6
	random_strength	1
	depth	6
	border_count	128
XGBoost	learning_rate	0.001
	n_estimators	1000
	max_depth	5
	min_child_weight	1
	gamma	0
	subsample	0.6
	colsample_bytree	0.8
	seed	27
GBDT	n_estimators	1000
	learning_rate	0.01
	max_depth	5
	random_state	4