Authors: Jianwei Gao, Zhonghua Chu
Addresses: School of Business Administration, North China Electric Power University, Beijing, 102206, China. ' School of Business Administration, North China Electric Power University, Beijing, 102206, China
Abstract: This paper focuses on the constrained portfolio selection problem and develops an improved particle swarm optimisation (IPSO) algorithm to solve it. As an alternative and extension to the standard Markowitz model, a constrained portfolio selection model with transaction costs and quantity limit is formulated for selecting portfolios. Due to these complex constraints, the process becomes a high-dimensional constrained optimisation problem. Traditional optimisation algorithms fail to work efficiently and heuristic algorithms with effective searching ability can be the best choice for the problem, so we design an IPSO to solve our problem. In order to prevent premature convergence to local minima, we design a new definition for global point. Finally, a numerical example of a portfolio selection problem is given to illustrate our proposed method; the simulation results demonstrate good performance of the IPSO in solving the complex constrained portfolio selection problem.
Keywords: swarm intelligence; particle swarm optimisation; improved PSO; IPSO; portfolio selection.
International Journal of Modelling, Identification and Control, 2010 Vol.9 No.1/2, pp.206 - 211
Published online: 01 Apr 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article