Stochastic Portfolio Selection Based on Velocity Limited Particle Swarm Optimization

Constructing a portfolio of investments is one of the most significant financial decisions facing individuals and institutions, modern portfolio theory is based on a rational investor choosing the proportions of assets in a portfolio so as to minimize risk and maximize the expected return. In this paper, the portfolio investment in which expected return rates are stochastic variables is studied and the velocity limited particle swarm optimization (VLPSO) algorithm is applied to solve this problem. First, the stochastic portfolio model and reliable decision are presented. Second, with the aim to overcome the local and global searching limitation of traditional numerical algorithms in the solution of nonlinear programming problems, a new global searching algorithm—velocity limited particle swarm optimization (VLPSO) is proposed. Finally, the effectiveness of the proposed VLPSO algorithm is demonstrated on a portfolio selection problem. Simulation results show that the VLPSO algorithm is effective and has potential to solve the portfolio management problem in real time.