A novel hybrid algorithm for mean-CVaR portfolio selection with real-world constraints

Qin, Quande; Li, Li; Cheng, Shi

Abstract

In this paper, we employ the Conditional Value at Risk (CVaR) to measure the portfolio risk, and propose a mean-CVaR portfolio selection model. In addition, some real-world constraints are considered. The constructed model is a non-linear discrete optimization problem and difficult to solve by the classic optimization techniques. A novel hybrid algorithm based particle swarm optimization (PSO) and artificial bee colony (ABC) is designed for this problem. The hybrid algorithm introduces the ABC operator into PSO. A numerical example is given to illustrate the modeling idea of the paper and the effectiveness of the proposed hybrid algorithm.

Citation

Qin, Q., Li, L., & Cheng, S. (2014). A novel hybrid algorithm for mean-CVaR portfolio selection with real-world constraints. Lecture Notes in Artificial Intelligence, 8795, https://doi.org/10.1007/978-3-319-11897-0_38

• Journal Article Type: Article
• Acceptance Date: Jan 1, 2014
• Publication Date: Sep 23, 2014
• Deposit Date: Oct 25, 2017
• Journal: Lecture Notes in Computer Science
• Electronic ISSN: 0302-9743
• Publisher: Springer Verlag
• Peer Reviewed: Peer Reviewed
• Volume: 8795
• Book Title: Advances in Swarm Intelligence
• DOI: https://doi.org/10.1007/978-3-319-11897-0_38
• Keywords: Conditional Value at Risk; CVaR; Hybrid algorithm; Port- folio selection
• Public URL: https://nottingham-repository.worktribe.com/output/735449
• Publisher URL: https://link.springer.com/chapter/10.1007%2F978-3-319-11897-0_38
• Additional Information: The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-11897-0_38
• Contract Date: Oct 25, 2017