optimal portfolio prediction in tehran stock market using multi-objective evolutionary algorithms, nsga-ii and mopso

despite the growing use of evolutionary multi-objective optimization algorithms in different categories of science, these algorithms as a powerful tool in portfolio optimization and specially solving multi-objective portfolio optimization problem is still in its early stages. in this paper, moeas have been used for solving multi-objective portfolio optimization problem in tehran stock market. for this purpose, non-dominated sorting genetic algorithm (nsga_ii) and multi-objective particle swarm optimization (mopso), as two common approaches, were compared with each other. using pareto front, investors can choose optimal portfolio based on different risks and returns. two objectives of the problem are return and risk of portfolio and cvar is the risk metric. in order to solve the problem, three real-world constraints were considered. the results indicate that these approaches have a high performance in constraint portfolio optimization.