Credit risk analysis using boosting methods

Abstract The use of credit for various occasions has become a routine in our lives. In return, banking and financial institutions require to determine whether the loan demands from them contain any risk. Accordingly, these have been increased their activities determining rating models past records person applying works properly. Machine learning-based technologies opened new era this field. AI machine learning based methods scoring are currently implemented by or non-banking institutions. Employed extract meaningful features required data which wide variety information available. study, risk assessment is conducted using boosting such as CatBoost, XGBoost Light GBM. To aim, Kaggle Home Credit Default Risk dataset used effect crediting tendency on results also considered. shown that gradient provide close each other, produces better AUC score CatBoost while it causes small decrement LightGBM.