鲁棒均值-半绝对偏差投资组合优化模型  

Robust Mean Semi-absolute Deviation Model for Portfolio Optimization

作　　者：戴志锋[1,2] 文凤华[2] 李董辉[3] 

机构地区：[1]长沙理工大学数学与计算科学学院,湖南长沙410114 [2]长沙理工大学经济与管理学院,湖南长沙410114 [3]华南师范大学数学科学学院,广东广州510631

出　　处：《系统工程》2012年第10期28-35,共8页Systems Engineering

摘　　要：讨论了鲁棒均值-半绝对偏差投资组合优化模型。假定资产收益的均值属于矩形和椭球不确定集，分别给出了矩形不确定集下和椭球不确定集下鲁棒均值-半绝对偏差投资组合优化模型，其中前者为线性规划（LP），后者为二阶锥规划（SOCP）。采用上海交易市场的实际交易数据对所提出的模型进行实证分析，结果表明鲁棒均值-半绝对偏差投资组合优化模型能够获得具有更好财富增长率的投资策略，及更稳定的回报。Abstract.. In this paper, the robust mean semi-absolute deviation models for portfolio optimization are discussed. Suppose the mean return of assets belonging to the box uncertainty set and ellipsoidal uncertainty set, the box uncertainty set-based robust mean semi-absolute deviation model for portfolio optimization and the ellipsoidal uncertainty set-based robust mean semi-absolute deviation model for portfolio optimization are proposed respectively. The first model is a Linear programming （LP） and the last one is a second-order cone programming （SOCP）, which all can be computed efficiently. The empirical analysis and comparisons from the real market data indicate that the robust models can obtain a portfolio strategy with the better wealth growth rate and more stable returns.

关 键 词：投资组合优化 均值-半绝对偏差 鲁棒优化 线性规划 二阶锥规划 

分 类 号：O224[理学—运筹学与控制论]