Credit Risk Assessment Based On Logistic Model

Personal credit is not only the ethical and moral basis for culture and market,but also a great resource for national economic development.The exploitation of personal credit resources can effectively optimize resource allocation,stimulate consumption and ultimately promote economic development.As a new form of private lending,P2 P lending has been introduced into China since 2006 and developing rapidly.However,due to the imperfection of the domestic personal credit system,it will give the borrower a great economic risk.Therefore,the research on the personal credit evaluation of P2 P loan is extremely important.Some developed countries had established their personal credit system as early as a hundred years ago,which laid a solid foundation for the market economy.In China,the establishment of personal credit system has just started.The researchs and applications of personal credit are far behind those of the developed countries.The personal credit score is the core of the personal credit system.The scientific assessment of personal credit situation will help to promote the development of personal credit business and reduce personal credit risk.Personal credit score is a set of data acquisition,missing data and abnormal data detection and processing,continuous data discretization,classification data re-coding,in dex system selection,model design,evaluation and application as one of the evaluation system.Based on the analysis of the development history of personal credit score at home and abroad and the application status of the method,the missing value of some samples of pterosaurs platform is effectively processed,and the continuous variable method is used to analyze the continuous variables Processing,which reduces the influence of the outliers of continuous variables on the prediction accuracy of the model.The results show that discretization can reduce the influence of outliers on personal credit score and improve the accuracy of model prediction.Secondly,when constructing the index system,we use the chi-square distribution to do the correlation judgment,use IV to do the quantification of the correlation degree,effectively remove the small independent variables,make the index system become refined,and then factor analysis The effective and reasonable personal credit comprehensive factor index system.Finally,Logistic model is used to analyze the personal credit evaluation,and the results are analyzed under the whole variable index system,LR index system,qualitati ve-quantitative index system and the comprehensive factor index system mentioned a bove.The results show that the comprehensive factor index system has more advantages in the prediction accuracy of the second type of false positive rate.