Portfolio Optimization Based on Cross Efficiencies By Linear Model of Conditional Value at Risk Minimization

Markowitz model is the first modern formulation of portfolio optimization problem. Relyingon historical return of stocks as basic information and using variance as a risk measure aretow drawbacks of this model. Since Markowitz model has been presented, many effortshave been done to remove theses drawbacks. On one hand several better risk measures havebeen introduced and proper models have been developed to detect optimized portfolio basedon them. On the other hand the idea of using generated data by data envelopment analysisinstead of historical return of stocks has been presented.In this paper, both improvements are collected by applying a conditional value at riskminimization linear model on cross efficiencies, generated by a proper model of dataenvelopment analysis model, called range adjusted model. Performance of proposedmethod, market portfolio as a benchmark and method of applying Markowitz model oncross efficiencies calculated according to sharp ratio using next year real return of eachportfolio during years of study. Results support proper performance of proposed method.