Forecasting Credit Risk of SMEs in Supply Chain Finance Using Bayesian Optimization and XGBoost

Table 5

Hyperparameters obtained by Bayesian optimization.

Hyperparameters	Definition description	Value
learning_rate	Learning rate	0.875
max_depth	Maximum depth of each tree	15
min_child_weight	Minimum sum of instance weight needed in a child	1
subsample	Subsample ratio of instances for each tree	0.8245
gamma	Minimum loss reduction required to make a split during tree building	0
colsample_bytree	Subsample ratio of features for each tree	0.726