Portfolio management assessment by four multiobjective optimization algorithm

The portfolio optimization aims to find an optimal set of assets to invest on, as well as the optimal investment for each asset. This optimal selection and weighting of assets is a multi-objective problem where total profit of investment has to be maximized and total risk is to be minimized. In this paper four well known multi-objective evolutionary algorithms i.e. Pareto Archived Evolution Strategy (PAES), Pareto Envelope-based Selection Algorithm (PESA), Adaptive Pareto Archived Evolution Strategy (APAES) algorithm and Non dominated Sorting Genetic Algorithm II (NSGA II) are chosen and successfully applied for solving the biobjective portfolio optimization problem. Their performances have been evaluated through simulation study and have been compared in terms of Pareto fronts, the delta, C and S metrics. Simulation results of various portfolios clearly demonstrate the superior portfolio management capability of NSGA II based method compared to other three standard methods. Finally NSGA II algorithm is applied to the same problem with some real world constraint.