Research on Credit Risk Prediction under Unbalanced Dataset Based on Ensemble Learning

Table 7

Comparison of experimental results of different oversampling methods.

Algorithm	F1-score	-mean	AUC	KS
RUSBoost	0.8537	0.5965	0.7465	0.3787
CUSBoost	0.9352	0.6341	0.7815	0.4452
KSMOTE-AdaBoost	0.9549	0.7056	0.7923	0.4536
BA-SMOTE-RAdaBoost-FLLGBM	0.9838	0.8739	0.8912	0.6053