Comparison of skewness and kurtosis effects for optimal portfolios risk criteria using dependent structure of copula functions

Portfolio optimization is one of the main methods of investment and one of the main stages of portfolio construction. Since ptimization is the process of selecting the best option from a set of available options, given specific constraints, this is one of the most important challenges facing investors, financial managers and operations research modelers. In this paper, the optimal portfolio curvature with criteria of variance risk (MV), absolute deviation (MAD) and conditional value at risk (CVaR) for the five symbols Shasta, Kachad, Vepars, Khsapa and Shebandar is obtained from 1/09/1399 to 1/3/1400 and all four methods are compared. Accordingly, the effect of skewness and kurtosis on optimal portfolios in all four risk criteria is investigated by applying the dependence structure of copula functions using Monte Carlo simulation. In this regard, Pearson distribution system and Gaussian copula have been used to simulate the yields with different skewness and kurtosis and with standard deviation and mean of historical data, and finally it is shown that this process leads to a change in the optimal portfolios in all four methods of portfolio optimization, so that the change in the amount of presented risk causes the most change in the optimal portfolio of CVaR and the least change in the optimal portfolio MSV.