Journal of Big Data

Table 6 Hyperparameter settings used in experiments

From: Data reduction techniques for highly imbalanced medicare Big Data

Classifier	Parameter name	Parameter setting
CatBoost	task_type	‘GPU’*
	max_ctr_complexity	1
	max_depth	5
ET	max_depth	8
XGBoost	max_depth	3
	tree_method	‘gpu_hist’*
LightGBM	max_depth	4
Random Forest	max_depth	4

*Setting selects Graphics Processing Unit (GPU) implementation of the classifier

Back to article page