Prediction based mean-variance model for constrained portfolio assets selection using multiobjective evolutionary algorithms

详细信息    查看全文

• 作者：Sudhansu Kumar Mishra^a ; ^{sudhansu.nit@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Ganapati Panda^b ; ^{ganapati.panda@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Babita Majhi^c ; ^{babita.majhi@gmail.com" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Constrained portfolio optimization ; Multiobjective optimization ; Functional link artificial neural network ; Efficient frontier ; Non-dominated sorting ; Nonparametric statistical test
• 刊名：Swarm and Evolutionary Computation
• 出版年：2016
• 出版时间：June 2016
• 年：2016
• 卷：28
• 期：Complete
• 页码：117-130
• 全文大小：1647 K

文摘

In this paper, a novel prediction based mean-variance (PBMV) model has been proposed, as an alternative to the conventional Markowitz mean-variance model, to solve the constrained portfolio optimization problem. In the Markowitz mean-variance model, the expected future return is taken as the mean of the past returns, which is incorrect. In the proposed model, first the expected future returns are predicted, using a low complexity heuristic functional link artificial neural network (HFLANN) model and the portfolio optimization task is carried out by using multi-objective evolutionary algorithms (MOEAs). In this paper, swarm intelligence based, multiobjective optimization algorithm, namely self-regulating multiobjective particle swarm optimization (SR-MOPSO) has also been proposed and employed efficiently to solve this important problem. The Pareto solutions obtained by applying two other competitive MOEAs and using the proposed PBMV models and Markowitz mean-variance model have been compared, considering six performance metrics and the Pareto fronts. Moreover, in the present study, the nonparametric statistical analysis using the Sign test and Wilcoxon rank test are also carried out, to compare the performance of the algorithms pair wise. It is observed that, the proposed PBMV model based approach provides better Pareto solutions, maintaining adequate diversity, and also quite comparable to the Markowitz model. From the simulation result, it is observed that the self regulating multiobjective particle swarm optimization (SR-MOPSO) algorithm based on PBMV model, provides the best Pareto solutions amongst those offered by other MOEAs.