Loan Portfolio Optimization Model Based On Higher Moments And Entropy

Loans are the largest resource for commercial banks.The use of loans not only determines the success of banking operations,but also has an important impact on social development.The optimal allocation of loan portfolios is a process that selects a suitable group of loans and allocates loans among the many loan applicants,by considering returns and risks of the loan portfolio.In the existing studies,the loan portfolio's return rate is usually calculated by using the historical data and does not consider the transfer of credit ratings.In fact,the credit rating of the loan is likely to change during the loan period,so the past return rate will not represent the future situation.Moreover,the distribution of real loan return is not entirely normal distribution,and the distribution of loan yields clearly shows biased and thick-tailed characteristics.In the loan portfolio optimization,if the degree of diversification of the loan portfolio is not measured and controlled properly,there may be a case where the loan is too concentrated,which leads to concentration risk.This academic dissertation is consists of four parts.The first chapter of this paper introduces background and significance of the research,the research status at home and abroad,and the research content and research framework of this article.The second chapter introduces the principle of loan portfolio optimization model based on higher moments and entropy,In the third chapter,we mainly discuss the establishment of loan portfolio optimization model based on higher moments and entropy.The fourth chapter is empirical study of the model.The main work of this paper: in this paper,the future expected return rate of the loan after the credit risk migration is measured according to the credit level migration probability matrix,and by using the future expected return rate of the loan,the VaR constraint,the skewness constraint,and the kurtosis constraint are constructed to control the risk of loan portfolio.The entropy of loan portfolio is used to control the degree of loan portfolio diversification.Finally,a loan portfolio optimization model based on higher moments and entropy is established and an example study is made.The main innovation and characteristics of this paper: the optimization model with four dimensional risk constraints,“VaR-skewness-kurtosis-entropy”,basing on the credit rating migration,controls not only the four dimensional risk of value at risk,left partial tail risk,bilateral tail risk and the concentration risk of portfolio,but also the risk related to creditrating migration.This model improves current research which only considerate static VaR,skewness and kurtosis without credit risk transfer,and changes the drawbacks of existing research which neglect the decentralizition of portfolio loan.