Author(s)

Pengcheng Sun

Corresponding Author

Pengcheng Sun

Abstract

Under the background of the development of big data and Internet finance, according to personal credit, we can effectively control the default rate of P2P projects to ensure the good operation of related financial projects or platforms. From the point of view of credit risk of P2P platform, taking the risk control of borrowers as the research objective, this paper constructs the evaluation index system of borrowers' credit, and establishes the evaluation model of borrowers' credit risk based on Light GBM algorithm using the data of P2P network lending platform. It has been proved by practice that the model can predict the credit risk of P2P network credit borrowers well and has high-precision classification ability. At the same time, based on the results of the Light GBM algorithm to determine the factors affecting the default rate, the improvement content of the P2P platform and the development direction of the countries in this field can be clarified.

Keywords

Light GBM Algorithm, P2P, Credit Rating