Loan Portfolio Optimization Model Based On CVaR And Improved Entropy

The loan business is the most important part of China's commercial bank asset projects.Its interest income is the bank's main source of operating income.Therefore,the study of the optimal allocation of loan portfolios is the focus of commercial bank operators and supervisory management departments,and it is also the main field of modern bank asset management and allocation theory research.With the slowdown of economic growth in China and the further opening up of China's financial industry,the pressure of competition among peers continues to increase.The “extensive” development model for commercial banks that only pursues the increase in the scale of credit assets is difficult to sustain,and the safety and profitability of credit assets is increased.The optimal allocation of loan portfolios considering sex and liquidity has become the key to the survivability and competitiveness of commercial banks.From the perspective of the overall risk of the entire loan portfolio and the degree of risk dispersion,this paper seeks to minimize the risk of all loans while pursuing the maximization of risk dispersion.At the same time,it introduces the minimum rate of return for loan portfolios determined by commercial banks based on actual conditions as a constraint.A full loan portfolio optimization model based on CVaR and improved entropy was constructed to achieve the objective of realizing expected return on the premise of controlling all loan portfolio risks.There are two main tasks in this article:(1)A multi-objective programming model for all loan optimization allocation is established,which the CVaR optimization principle based on the Laplace distribution is used to control the minimization of the overall risk,and the improved entropy is used to control the maximization of the risk dispersion of all loan portfolios.(2)This paper constructs two comparison models,the risk control optimization model only considering of “incremental” loans and the full loan portfolio optimization model based on CVaR and proportional entropy.Next the two comparison model are used to compare and analyze with this model is optimized with a full loan portfolio based on CVaR and improved entropy,to further prove the validity of the model.There are three main innovations and characteristics of this paper.The first is to measure the degree of diversification of all loan portfolios by introducing adjustment coefficient into the proportionality entropy to improve the entropy,which improves the proportionality entropy only considering the risk decentralization from the perspective of loan allocation weight and ignoring the disadvantages of the relationship between income and risk,and makes the measurement of decentralization of all loan portfolios more reasonable.Secondly,the multi-objective programming model is established by controlling the total portfolio risk after the combination of stock portfolio and incremental portfolio to get the optimal allocation of incremental assets.Changed the popularity of research only to control the lack of incremental risk,which Changes the lack of only incremental risk is controlled in the popular research.Thirdly,the risk control of all loan portfolio is the basis of the loan return rates followed a Laplace distribution assumption,in line with the "rush fat tails" features of the return on financial assets,which makes risk can accurately assessed and improves the research based on the normal distribution assumption can not accurately fit the actual distribution of the loan rate of return,and thus can not reasonably estimate the disadvantages of the risk.