IDEAL AND ANTI-IDEAL COMPROMISE PROGRAMMING FOR ROBUST Bi-OBJECTIVE PORTFOLIO SELECTION PROBLEM

This paper proposes a robust optimization approach for biobjective portfolio selection problem. We propose mean-CVaR as a bi-objective model and in this model we consider parameter uncertainty. We use Bertsimas and sim approach to consider uncertainty in the model and we by to use ideal and anti-ideal compromise programming to solve model. This solving approach is better than compromising and goal programming approach for portfolio selection problem because this approach tries to increase the distance of the solution and anti-ideal criteria that in our model is CVaR and on the other hand tries to decrease the distance between expected rate of return of portfolio and the solution. Efficiency of this model is tested by real life data.