Multi-objective particle swarm optimization approach to portfolio optimization

The problem of portfolio optimization is a standard problem in financial world and has received a lot of attention. Selecting an optimal weighting of assets is a critical issue for which the decision maker takes several aspects into consideration. In this paper we consider a multi-objective problem in which the percentage of each available asset is selected such a way that the total profit of the portfolio is maximized while total risk to be minimized, simultaneously. Four well-known multi-objective evolutionary algorithms i.e. Parallel Single Front Genetic Algorithm (PSFGA), Strength Pareto Evolutionary Algorithm 2(SPEA2), Nondominated Sorting Genetic Algorithm II( NSGA II) and Multi Objective Particle Swarm Optimization (MOPSO) for solving the bi-objective portfolio optimization problem has been applied. Performance comparison carried out in this paper by performing different numerical experiments. These experiments are performed using real-world data. The results show that MOPSO outperforms other two for the considered test cases.