Analysis Of Portfolio Strategy Based On Mean-CrVaR Model

After years of development,China's securities market has made great progress.The market mechanism has been increasingly perfected,systemic risks have been well controlled,and risks have gradually weakened.Non-systematic risks in the market have begun to become major in the market.The type of risk has an increasing impact on the securities market.Faced with this development background,in order to reduce risks,more and more investors began to participate in investments in the form of securities investment portfolios in order to achieve the goal of risk diversification.The importance of modern investment theory has become increasingly prominent,modern investment theory,traditional Markowitz theory is one of the representative theories.In this theory,the investment risk is measured by the variance,and the advantage is that the calculation is simple and easy to implement.However,there are also deficiencies in this approach because the variance is mainly an analysis of the degree of deviation of returns,and there is no accurate estimate of the losses that the portfolio may cause.Based on this,in order to solve this problem,scholars began to study how to improve the theory.Many scholars began to try to introduce new risk measurement tools into the traditional Markowitz theory for analysis,such as the mean-VaR(Value-at-risk).In the risk value)and the mean-CVaR(Conditional Value-at-risk condition in the insurance value)model.Based on the above background,this paper establishes the mean-CrVaR model(Credible Value-at-risk credible risk value),uses the CrVaR risk measure to measure the risk,and is similar to the mean-VaR model,and evades the solution by solving the optimal solution of the portfolio.risk.In the process of modeling and solving the model,a comparative analysis was conducted and the following conclusions were drawn:(1)Since VaR does not satisfy the subadditivity in the axiom of consistency,the VaR value of the portfolio is greater than the sum of the VaRs of the components in the portfolio.This obviously does not meet our risk aversion strategy.However,CrVaR,the risk measurement method used in this paper,is consistent and effectively compensates for the VaR deficiencies,which can measure risks more effectively.(2)For a CVaR risk measure that also satisfies consistency,the CrVaR risk measure can be measured more accurately than the CVaR model by comparing the values of prior information and historical data when calculating VaR.The effective frontier of CVaR and mean-CrVaR models shows that the CrVaR corresponding to the mean-CVaR model is greater than the CrVaR corresponding to the mean-CrVaR model when the expected rate of return is the same,that is,if the risk measurement method is consistent,the mean-CrVaR investment The combined optimization model can better control the portfolio risk than the mean-CVaR model.(3)For the identified alternative assets,the effective frontier of the portfolio based on the mean-CrVaR model differs from the mean-variance model in only one effective frontier,and the effective frontier of the portfolio will change with different levels of confidence.Assuming that the weight of the original stock portfolio is unchanged,only the confidence level is increased from 90% to 95%,and the corresponding CrVaR value will increase as the confidence level increases.