Applying a nonparametric random forest algorithm to assess the credit risk of the energy industry in China

With the rapid growth of the credit card business in China's energy industry, credit risk is gradually revealed. This study aims to scientifically measure the credit risk of credit cards used in China's energy industry and to lay the foundation for comprehensive credit risk management. Based on an analysis of the factors influencing credit risk influencing factors, this study applies the random forest algorithm and the monthly data of credit cards used by energy industry customers in a branch of the Postal Savings Bank of China from April 2014 to June 2017 to build an effective credit risk assessment model and scientifically measure the credit risk in China's energy industry. The results suggest that credit card features like the overdraft ratio and the amount of credit card expenses within a month have significant impacts on credit risk, our model's comprehensive prediction accuracy is as high as 91.5%, and its stability is satisfying. These findings can provide valuable information to help banks improve their credit risk management.