数据驱动的扭曲均值-半方差投资组合选择

Mean-Semivariance Portfolio Selection with Distortion Based on a Data Driven Approach

运用样本平均近似的数据驱动方法研究了带概率扭曲的均值-半方差投资组合优化模型,结合经典的遗传算法(ICA)和帝国竞争算法(GA),提出了ICA-GA混合算法.利用真实市场数据,对模型进行实证分析并求解有效前沿.最后,通过比较算法程序运行时间,表明本文创新的ICA-GA混合算法融合了帝国竞争算法和遗传算法两者的优势,比它们有更好的表现.

This paper studies a mean-semivariance portfolio optimization problem with probability distortion by using the data driven sample average approximation(SAA)approach.The paper builds ICA-GA hybrid algorithm based on the traditional imperial competitive algorithm(ICA)and genetic algorithm(GA).Employing the true market data,the model is empirically analyzed and the effective frontier is solved.Finally,by comparing the running time of the computer programs,it shows that the ICA-GA hybrid algorithm in this paper combines the advantages of imperial competitive algorithm and genetic algorithm,and it performs better than them.