The problems about some borrowers default in the rapid development of P2P network loan causes economic losses to online lending platforms and investors. Based on the situation of borrowers repaying loans in installments, this paper uses automatic binning to select features, builds a risk monitoring model, and predicts whether the borrower will perform next month. The model can discover the signs of borrower's default in advance, so that the platform can take preventive measures earlier and

more »

... nt the problem of platform fund circulation caused by insufficient repayment. In addition, it can provide reference for the platform to estimate the monthly payment amount. In this paper, the borrower data of 2016-2018 on Lending Club is used. The risk monitoring models of borrowers are based on CART algorithm, random forest algorithm and XGBoost algorithm respectively. The precision accuracy of the algorithms above is above 95%. The repayment amount of borrowers at last month, the borrower's occupation, the total amount of borrowing, the borrower's monthly repayment amount, and whether the borrower is working with the debt settlement company which are very effective in analyzing the willingness of the borrower to perform on time next month. Therefore, they could be used as the main basis for analysis.