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

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.