基于DEClu算法的均值-VaR投资组合优化  

Mean-VaR Portfolio Optimization Based on DEClu Algorithm

作　　者：陈敏 赵新超[1] CHEN Min;ZHAO Xin-chao(School of Science,Beijing University of Posts and Telecommunications,Beijing 100876)

机构地区：[1]北京邮电大学理学院,北京100876

出　　处：《软件》2018年第10期79-86,共8页Software

摘　　要：投资组合问题是一个复杂的非线性规划问题,传统的算法难以有效求解。本文将新提出的基于聚类的差分算法用于求解均值-VaR模型,用罚函数方法处理模型中的不等式约束,选取雅虎财经中的50支股票作为备选股票进行实证分析,数值结果表明,该算法取得了良好的效果,解的结果既满足了投资的目标和约束条件,又反映了投资者之间不同的收益风险需求,且具有较好的实践性。The investment portfolio problem is a complex nonlinear programming problem, which belongs to NP-hard problem. The traditional algorithm is difficult to solve the problem effectively. In this paper, the newly proposed cluster-based differential algorithm is used to solve the mean-VaR model, the penalty function method is used to deal with the inequality constraints in the model, and 50 stocks in Yahoo Finance are selected as the alterna-tive stocks for empirical analysis. Numerical results show that the new algorithm of this paper has achieved good results. The results of the solution not only satisfy the objectives and constraints of the investment, but also reflect the different income and risk requirements among investors, and it has good practicality.

关 键 词：聚类分析 差分算法 投资组合 均值-风险价值(VaR) 

分 类 号：TP315[自动化与计算机技术—计算机软件与理论]