Implementation of particle swarm optimization in construction of optimal risky portfolios

• Published in: 2007 IEEE International Conference on Industrial Engineering and Engineering Management pp. 812 - 816
• Main Authors: Dashti, M.A., Farjami, Y., Vedadi, A., Anisseh, M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2007
• Subjects: Asset management; Dynamic programming; Engineering management; Investments; modern portfolio theory; Neural networks; optimal risky portfolio; Optimization methods; Particle swarm optimization; Portfolios; PSO; Risk management; Sharpe ratio; Testing
• ISBN: 1424415284; 9781424415281
• ISSN: 2157-3611; 2157-362X
• DOI: 10.1109/IEEM.2007.4419303

Since Markowitz's substantial work, the mean-variance model has revolutionized the way people think about portfolio of assets. According to the modern portfolio theory, the fundamental principle of financial investments is a diversification where investors diversify their investments into different types of assets. Constructing an optimal risky portfolio is a high-dimensional constrained optimization problem where financial investors look for an optimal combination of their investments among different financial assets with the aim of achieving a maximum reward-to-variability ratio. Among the various methodologies suggested, the most popular one is based on maximizing the well-known Sharpe ratio. In this study, we apply particle swarm optimization (PSO) for constructing optimal risky portfolios based on Sharpe ratio for financial investments. A particle swarm solver is developed and tested on a risky investment portfolio. The method is applied to a sample of stocks in Tehran Stock Exchange. Experimental results reveal that the proposed PSO algorithm provides a very feasible and useful tool to assist the investors in planning their investment strategy and constructing their portfolio.