Study On Credit Risk Perdiction Of The Listed Companies In China

Credit risk is the main risk facing the modern economic system,and the financial situation of the company has a direct impact on it.With the development of financial markets,the emergence of new financial instru-ments to expand the scale of financial derivatives transactions,these cred-it derivatives rapidly expanding the scope and scale of credit risk invo-lved.How to accurately measure credit risk and further manage it effe-ctively has become one of the most challenging issues facing comm-ercial Banks.The purpose of this paper is to predict the existence of credit risk of listed companies in China,using the classification model Logistic regression model to predict it,and choose financial indicators of listed companies as model covariates.Based on the large number of financial indicators of listed companies and strong correlation characteristics when the number of financial indicators d is larger than the sample size n,the penalty method is selected firstly,so that d<n;followed by principal component analysis to select the main components,which further reduce the spatial dimension of financial indicator data,and get the irrelevant principal components.Based on it,the logistic regression model is used to predict the credit risk by the principal component as the covariable.In the empirical part,63 listed companies are selected as the research sample,among them 27 ST companies and 36 non-ST companies,a total of 106 financial indicators were selected as variables to construct the model from the seven aspects of indicators per index,capital structure,cash flow,solvency,operational capability,profitability and growth ability.The empirical results show that the model has a good prediction effect,with an accuracy of 87.3%and an AUC of 86.1%.The structure of this paper is as follows.The first chapter is the introd-uction part,discusses the research background and significance of credit risk,reviews the previous scholars' research on credit risk,and puts forward the research framework and innovation point of this paper.The second chapter discusses the basic theory of credit risk,based on it we discuss the selection of the financial indicators to predict the credit risk of listed companies in China.The third chapter introduces the basic theo-retical knowledge of all the models involved in the credit risk prediction of listed companies in this paper.The fourth chapter gives the framework of credit forecasting system construction and model test theory.The fifth chapter and the sixth chapter are simulation experiments and empirical analysis.The last chapter summarizes this paper and points out the basis for further research.