The optimal portfolio model based on multivariate t distribution with linear weighted sum method

This paper proposed the optimal portfolio model maximizing returns and minimizing the risk expressed as CvaR under the assumption that the portfolio yield is subject to the multivariate t distribution. With linear weighted sum method, we solved the multi-objectives model, and compared the model results to the case under the assumption of normal distribution return, based on the portfolio VAR through empirical research. It is showed that our max return equals to and risk is higher than M-V model. It shows that CVaR predicts the potential risk of the portfolio, which is helpful for investor’s cautious investment.