具有联合椭圆不确定集与概率约束的鲁棒投资组合选择  

Robust portfolio selections with joint ellipsoidal uncertainty set and probability constraints

作　　者：凌爱凡[1] 吕江林[1] 

机构地区：[1]江西财经大学金融与统计学院,南昌330013

出　　处：《控制与决策》2011年第4期558-564,570,共8页Control and Decision

基　　金：国家自然科学基金项目(71001045;10971162);国家社会科学基金项目(BJY145);江西省教育厅青年科技项目(GJJ10114)

摘　　要：针对参数在一个联合椭圆不确定集中变化的情形,建立了一个具有概率约束的鲁棒投资组合模型,并将其转化为可由内点算法求解的含线性矩阵不等式(LMI)约束的凸规划问题.应用实际交易数据对所提出的模型进行数值实验和比较,结果表明此模型能够获得具有更好财富增长率的投资策略,并能有效地分散最优投资组合的风险.A robust portfolio selection model with probability constraints is established under the assumptions that parameters of model vary in a joint ellipsoidal uncertainty set.Then the proposed problem is converted into a convex programming problem with LMI constraints that can be solved by using interior point algorithms.The empirical analysis and comparisons from the real market data indicate that the proposed model can obtain a portfolio strategy with the better wealth growth rate and diversify the risk of the optimal portfolio efficiently.

关 键 词：鲁棒优化 投资组合 椭圆不确定集 概率约束 线性矩阵不等式 

分 类 号：F224.3[经济管理—国民经济] O221[理学—运筹学与控制论]