Handling Problems of Credit Data for Imbalanced Classes using SMOTEXGBoost

Abstract Some researchers find data with imbalanced class conditions, where there are a number of minorities and majority. SMOTE is approach for an classes XGBoost one algorithm problems. This research uses or abbreviated as SMOTEXGBoost handling classes. The results showed almost the same accuracy value between at 99%. While AUC SMOTEXBoost has more stable than that equal to 99.89% training 98.51% testing.