Empirical Analysis Of Credit Risk Measurement Of Commercial Banks Based On KMV Method

At present,the credit risk management level of commercial banks in developed countries has been very mature,and a relatively advanced system has been formed at the theoretical and practical levels.It presents a development trend from qualitative to quantitative,from traditional to modern,from individual credit risk rating to portfolio credit risk rating.The methods and models of credit risk measurement are constantly updated and iterated.In contrast,the credit risk management system of commercial banks in China is not perfect,and the credit rating is still at the primary level.However,the volatility of financial markets is increasing,the problem of credit risk is increasingly prominent.The assessment and measurement of default risk should be paid more and more attention.Firstly,this paper compares and analyzes several modern credit risk management measurement models including KMV model,analyzes and compares the theoretical basis,advantages and disadvantages and applicability in detail,and analyzes the application status and adaptability of KMV model in credit risk measurement of commercial banks in China.It is considered that KMV model is more suitable for measuring customer credit risk of commercial banks in China.Then it expounds the modeling idea of KMV model,compares and analyzes the practicability of Logit model and KMV model in credit risk measurement,and innovatively uses descriptive statistics and independent T test to determine whether the default distance can significantly distinguish between normal companies and default companies.On the basis of the test,the KMV-Logit mixed model is used for empirical analysis,and compared with the benchmark Logit model.It is found that in terms of discrimination accuracy,the KMV-Logit mixed model with default distance is much butter than that of the Logit model.It shows that after adding default distance,the improved combination model is not only more convincing in the goodness of fit of the model,reflecting the objectivity and effectiveness of the model as a whole,but also greatly improves the accuracy of credit risk measurement of listed companies.