Research On Credit Risk Assessment Of Microfinance Based On BP Neural Network

The initial purpose of microcredit was to help the poor,and later the object of service became more extensive and gradually turned to commercialization.Since the1970 s,microfinance has grown from scratch.In the economic development,microfinance played an important role.At the same time,in the rapid development of micro-credit also contains a variety of risks,credit risk is one of them.Credit risk is the risk that the borrower will not be able to repay the loan on the due date or will not pay the loan to the lender.The accuracy of the credit risk assessment of microcredit is related to the development of small loan industry.In this paper,the concept of microfinance is described in detail,and the relevant theory is sorted out.After comparing the relevant credit risk assessment model,the BP neural network model is selected as the model to evaluate the credit risk of microfinance.BP neural network model has a strong learning and reasoning ability,a strong simulation ability,and able to deal with non-linear relationship,these advantages is required to the assessment of micro credit credit risk.On the basis of the existing literature,this research has been innovated in the design of credit risk assessment index system and BP neural network structure design.After that,the BP neural network model is established by using the data obtained in this paper,and the ideal result is obtained.Moreover,the BP neural network model obtained in this study has been recognized by the industry and can provide reference for the credit credit risk assessment.This paper concludes that:(1)microfinance was originally born for the purpose of poverty alleviation and gradually shifted from poverty alleviation to commercialization in later development;(2)credit risk is one of the major risks of microfinance,and lower credit risk can be achieved by reducing information asymmetry,establishing default penalties and enhancing borrower's ability of controlling risk;(3)in the micro credit risk assessment,the BP neural network model has some unique advantages;(4)in this paper,Through the empirical analysisof the credit risk assessment,it found that the correctness of the model established in this study is higher than that of the non-default.For microfinance credit risk evaluation problem,this paper puts forward the feasible countermeasures are:(1)improve the credit system construction,and reduce the information asymmetry;(2)establish microfinance default penalty mechanism;(3)strengthen the borrower's credit consciousness,and improve their ability of controlling risk;(4)improve the microfinance credit risk evaluation system;(5)improve the BP neural network model.