Bi-Objective Portfolio Optimization with Mean-CVaR Model: An Ideal and Anti-Ideal Compromise Programming Approach

Portfolio optimization is an important topic in the financial management literature. This problem consists of managing wealth across available assets to gain maximum profit with the least amount of risk. In this paper, a novel approach for mean conditional value at risk (Mean-CVaR) as a bi-objective portfolio optimization problem is proposed. In order to address mean-CVaR, we utilized an ideal and anti-ideal compromise programming approach. Compared to compromise programming and goal programming, this approach is more efficient for solving the portfolio optimization problem, as it aims to increase the distance between solutions and anti-ideal criteria. This research utilizes a real-life case study from the Tehran Stock Exchange (TSE) to demonstrate the effectiveness of the proposed approach. The computational results determined the effectiveness of the solution methodology and it could be applied quite reliably in other engineering contexts without a significant degradation in performance.