Portfolio selection using an artificial immune system

This paper presents a novel heuristic method for solving a generalized Markowitz mean-variance portfolio selection model. The generalized model includes two types of constraints; bounds-on-holdings and cardinality constraints. The former guarantee that the amount invested (if any) in each asset is between its predetermined upper and lower bounds while the latter ensures that the total selected assets in the portfolio is equal to a predefined number. The generalized model is, thus, classified as a quadratic 0/1 integer programming model necessitating the use of efficient heuristics to find the solution. Some heuristic methods based on Genetic Algorithm, Simulated Annealing, Tabu Search and Neural Networks have been reported in the literatures. In this paper, we propose a novel heuristic based on an artificial immune system. The proposed approach is illustrated and compared with other methods using five sample set of data utilized by other researchers. The computational results show that the proposed approach can effectively solve large-scale problems.