P2P Default Risk Prediction based on XGBoost, SVM and RF Fusion Model

Abstract

In the P2P platform, the problem of overdue repayment of users often occurs. This phenomenon seriously damages the interests of the platform and creditors. Therefore, how to improve and improve the risk monitoring capability of the P2P online lending platform and reduce the investment risk of investors is the future development of the P2P online lending industry. Very important question. To solve this problem, this paper proposes a P2P default risk prediction model based on XGBoost, SVM and RF fusion model. The model uses the stacking model set framework to model XGBoost, SVM and RF, and combines the advantages of high accuracy, robustness and generalization ability of the three models. The proposed fusion model has better prediction. Effect.