A constrained portfolio selection model at considering risk-adjusted measure by using hybrid meta-heuristic algorithms |
| |
Affiliation: | 1. School of Economics & Management, Xidian University, Xi''an 710126, China;2. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China;3. LeBow College of Business, Drexel University, Philadelphia, PA 19104, USA;4. School of Management, Wuhan University of Technology, Wuhan 430070, China |
| |
Abstract: | Portfolio selection is a key issue in the business world and financial fields. This article presents a new decision making method of portfolio optimization (PO) issues in different risk measures by using new evolutionary computing method and cardinality constrains which is mentioned as hybrid meta-heuristic algorithms. Based on mean–variance (MV) Method by Markowitz we collected three risk levels; mean absolute deviation (MAD), semi variance (SV) and variance with skewness (VWS). The developed algorithms are Electromagnetism-like algorithm (EM), particle swarm optimization (PSO), genetic algorithm (GA), genetic network programming (GNP) and simulated annealing (SA). Also a diversification mechanism strategy is implemented and hybridized with the developed algorithms to increase the diversity and overcome local optimality. The sustainability of this proposed model is verified by 50 factories on the Iranian stock exchange. Finally, experimental results of proposed algorithms with cardinality constraint are compared with each other by four effective metrics in which the algorithms performance for achieving the optimal solution discussed. In addition, we have done the analysis of variance technique to confirm the validity and accurately analyze of the results which the success of this method was proved. |
| |
Keywords: | Portfolio optimization Hybrid meta-heuristic algorithms Iranian stock exchange Mean–variance Mean absolute deviation Semi variance Variance with skewness |
本文献已被 ScienceDirect 等数据库收录! |
|