Loan default prediction of Chinese P2P market: a machine learning methodology

Abstract

Repayment failures of borrowers have greatly affected the sustainable development of the peer-to-peer (P2P) lending industry. The latest literature reveals that existing risk evaluation systems may ignore important signals and risk factors affecting P2P repayment. In our study, we applied four machine learning methods (random forest (RF), extreme gradient boosting tree (XGBT), gradient boosting model (GBM), and neural network (NN)) to predict important factors affecting repayment by utilizing data from Renrendai.com in China from Thursday, January 1, 2015, to Tuesday, June 30, 2015. The results showed that borrowers who have passed video, mobile phone, job, residence or education level verification are more likely to default on loan repayment, whereas those who have passed identity and asset certification are less likely to default on loans. The accuracy and kappa value of the four methods all exceed 90%, and RF is superior to the other classification models. Our findings demonstrate important techniques for borrower screening by P2P companies and risk regulation by regulatory agencies. Our methodology and findings will help regulators, banks and creditors combat current financial disasters caused by the coronavirus disease 2019 (COVID-19) pandemic by addressing various financial risks and translating credit scoring improvements.

Drivers and consequences of borrowers' voluntary privacy information disclosure—Evidence from a Chinese online consumer financing platform

“…Third, our study adds to the loan default prediction literature (Xu et al, 2021) by revealing the diagnostic value of different types of private information in predicting loan defaults. Specifically, we find that high-cost information is more effective in confirming borrowers who repay and do so on time, whereas low-cost information is more valuable in identifying loan defaults.…”

“…First, more information disclosure does not necessarily represent borrowers' quality in funding repayment. For example, certain information that borrowers provide is not verified onsite, which may be reflected in a higher probability of repayment failure (Xu et al, 2021). Second, borrowers with different credit ratings may exhibit distinct disclosure motivations.…”

Predicting acceptance of the bank loan offers by using support vector machines

“…Xu et al used 4 machine learning methods (RF, XGBT, GBM, and NN) to predict factors affecting repayment of borrowers. They conclude that the RF performs well in the classification task of default [12]. Huang et al explain that SVM and NN achieve better prediction accuracy than traditional statistical methods in credit rating analyses for the US and Taiwan markets [13].…”

Financial distress prediction using integrated Z-score and multilayer perceptron neural networks

“…Hamori et al [ 22 ] used bagging, random forest, and boosting and compared with neural network models., Kim et al [ 27 ] used machine learning algorithms logistic regression, random forest, support vector machine and feedforward neural network models. [ 33 ]) used random forest, extreme gradient boosting tree, gradient boosting model, and neural network models. Thus we see that there are many variants of machine learning models applied.…”