Robust Portfolio Optimization with risk measure CVAR under MGH distribution in DEA models

Financial returns exhibit stylized facts such as leptokurtosis, skewness and heavy-tailness. Regarding this behavior, in this paper, we apply multivariate generalized hyperbolic (mGH) distribution for portfolio modeling and performance evaluation, using conditional value at risk (CVaR) as a risk measure and allocating best weights for portfolio selection. Moreover, a robust portfolio optimization and performance evaluation modeling in mGH framework are developed, using worst case CVaR (WCVaR) as a risk measure. Due to the fact that expected returns can take negative values, the introduced model is inspired by Range Directional Measure model. Finally, real data in Iran stock market are given to illustrate the effectiveness of the model.