Study On The Credit Risk Eva1uation Models Of Listed Companies In China

With the rapid growth of global economy,problems related to credit risk have attracted much attention. Credit risk has became one of the important risks which financial institutions have to face. For that,how to control and get an accurate estimation of credit risk plays a key role in the decision making to financial intermediaries,investors and govemment supervisor. Listed company is an important part of our national economy, which is the basis of the securities market. The quality of the company,the normative acts and their financial situation will affect the development of securities market of China and the interests of investors directly. Under this international finance background,this paper select credit risk of listed companies in China as its research subject.The paper introduces the concept and the charaeteristics of credit risk,establish suitable model for credit risk measurement of listed companies in China,there by enhancing our credit risk management capabilities. Firstly,a brief account of the traditional"5C"experts law,credit score and credit rating of traditional credit risk measurement methods;Then, focus on the modern credit risk measurement model,J.P.Morgan Credit Metries,KMV model researched and developed by KMV company,Credit Risk+ model,and Credit Portfolio View model. The paper focus on the theoretical basis and the adaptability of the study in China. On this basis,according to the default condition in listed companies in China, factor analysis combined with logistic regressions analysis have been introduced into research on credit risk of listed company, and pick out financing indices that showing us the credit risk value. Then select correlative data of listed companies of China,uses the factor analysis to abstract all kinds of factors separately. It developed credible and effective credit risk financial index system of listed companies in China,enriched the relevant researching theory over credit risk measurement. We have formed our listed companies'credit risk default discrimination model, follows logistic theoretie model.As the precision of the credit risk default discrimination model affect the bank's risk status and profit levels directly, Bayes Estimator has been used to improve the standard logistic model in , aims to improve predictive power of credit risk default discrimination models. Then compare the precision of two models by AUC value and Brier Score , result shows that the value of AUC of standard estimator is 0.834, Bayesian Estimators is 0.870, which is 3.6 percentage points higher than the standard estimator. It proved that the Bayes Estimator has a higher predictive power of precision and stability.