Credit Risk Measurement Of P2P Networks Loans Based On Logistic

P2P lending is an Internet-based network and independent thinking outside the formal financial system lending transaction mode. As of the end of March 2015 the number of P2 P network operators lending platform has reached 1728, total turnover has reached 500 billion yuan. Excessive growth of the platform, the lack of effective regulation, is an important factor leading to the risk of P2 P net loan platform platform frequent incidents and problems increased. Coupled with sustained domestic economic structure adjustment in depth, slowdown in economic growth, the economic impact of increased downward pressure on credit risk exposure P2 P net loan industry continues to rise.P2P lending platform network profit by business risk, the risk management technology is the core competitiveness of P2 P net loan platform, but also in the main line of development has been through P2 P net loan industry for some time. The reason this paper produced from the credit risk of loans to start P2 P network, and a brief introduction to credit risk measurement models, combined with the actual situation of P2 P net loan, select Logistic regression model for P2 P network loan credit risk measurement and prediction. The size of the borrower’s default rate is mainly affected by the borrower and loan status to their own situation, so select the text borrower qualifications, age, loan amount, interest rate and other indicators, and by the principal component analysis, the number of explanatory variables is reduced to 4 a. Logistic model by empirical analysis, the specific expression, the model results show that the probability of default and is inversely proportional to the level of education and other factors and the four indicators borrower’s loan amount, duration, etc. are directly proportional to the risk of default of the borrower, realistic case, then the sample data sets within-sample data sets and verify the model were also higher prediction accuracy rate, indicating that the use of P2 P networks Logistic regression models to measure credit risk is feasible and reliable.