Symbiotic Multi-swarm PSO for Portfolio Optimization

摘要

This paper presents a novel symbiotic multi-swarm particle swarm optimization (SMPSO) based on our previous proposed multi-swarm cooperative particle swarm optimization. In SMPSO, the population is divided into several identical sub-swarms and a center communication strategy is used to transfer the information among all the sub-swarms. The information sharing among all the sub-swarms can help the proposed algorithm avoid be trapped into local minima as well as improve its convergence rate. SMPSO is then applied to portfolio optimization problem. To demonstrate the efficiency of the proposed SMPSO algorithm, an improved Markowitz portfolio optimization model including two of the most important limitations are adopted. Experimental results show that SMPSO is promising for this class of problems.