Abstract:

The Markowitz portfolio optimization model has certain di¢ culties in practise since real data are rarely certain. The robust optimization isa recently developed method that is used to overcome the uncertainty situation. The technique has been recently suggested in the portfolio selectionproblems. In this study, two kinds of portfolio optimization problems are presented: (i) the risk aversion portfolio optimization problem based on the classical Markowitz framework, and (ii) the max-min counterpart problem basedon the robust optimization framework. In the application, the two models areperformed on a real-world data set obtained from BIST (Borsa Istanbul). Numerical results show that the ob jective function values of the classical solutionand the robust solution are similar to each other. It can be said that the robustmodel, which works as well as the classical model in the uncertainty situations,can be used instead of the classical model and also that the optimal solutionobtained in the uncertainty situation is robust to parameter perturbation

Keywords: