Font Size: a A A

A Comparative Study On The Credit Risk Identification Of Private Listed Companies With Dual Model Prediction Method

Posted on:2021-01-28Degree:MasterType:Thesis
Country:ChinaCandidate:Y WangFull Text:PDF
GTID:2439330629982707Subject:Project management
Abstract/Summary:PDF Full Text Request
Since the reform and opening-up,China has made great achievements in various fields,and the pace of development has shocked the world.Among them,private enterprises played an important role in promoting the development of economy,taxation,and market,especially in the fields of job creation and technological innovation.At the symposium on private enterprises held in 2018,the necessity and importance of vigorously supporting the development of private enterprises were emphasized again.Subsequently,the CIRC also made a series of policies to support and protect the development of private enterprises.However,in recent years,the non-performing loan rate of commercial banks continues rising,among which a large proportion is loans from private enterprises,indicating that the credit risk of private enterprises is still one of the main themes of today's financial market.If we can accurately identify and forecast these credit risks,the non-performing loan rate of commercial banks can be greatly reduced,so that we can have more funds to help private enterprises in developing and fulfill the duties of supporting private enterprises earnestly.In this paper,the credit risk factors of private enterprises were quantitatively studied from a scientific perspective to find out the decisive factors,and the credit risk index system of private enterprises was designed by using the factor analysis method.Logistic model and GA-BP neural network model were constructed to contrastively analyze the credit risk of private enterprises.According to the results,in terms of explanatory ability,Logistic model was better.It can judge the importance of variables and at the same time assess the importance of relevant variables to the risk of credit default.In terms of prediction ability,GA-BP neural network model had higher accuracy.Based on the above results,a set of credit risk warning mechanism for private enterprises was established for China's commercial banks.Reasonable risk control measures were formulated according to different risk warning indicators,and key indicators of credit risk of private enterprises were explored to reduce monitoring costs.It provides theoretical basis and technical support for commercial banks to effectively reduce the credit risk of private enterprises.At last,the development and improvement of credit risk management of private enterprises was put forward.
Keywords/Search Tags:Private enterprises, Credit risk, Logistic regression, Genetic algorithm, BP neural network
PDF Full Text Request
Related items