A Comparative Study of Multi-Objective Multi-Period Portfolio Optimization Models in a Fuzzy Credibility Environment Using Different Risk Measures

The purpose of the present research is to compare portfolio optimization models in a fuzzy credibility environment, aimed for end-of-period wealth maximization and risk minimization. The investor’s risk was measured using the Value at Risk (VaR), Average Value at Risk (AVaR) and semi Entropy. In order to get closer to the real world investment model, while allowing for transaction costs and investing part of wealth in risk-free assets, in addition to the cardinal constraints, other constraints including the minimum and maximum amount of wealth assigned to each asset, and the minimum and maximum number of stocks present in portfolio were applied. The results of the multi-period models running by MOPSO algorithm indicated for the models Mean-AVaR, Mean-Semi Entropy, and Mean-VaR, respectively, performed better, in terms of Sharp and Treynor measures.