带交易费用的离散多因素投资组合最优化(英文)

Discrete Multi-factor Portfolio Optimization Model with Transaction Cost

研究带有凹的交易费函数的离散多因素投资组合模型.与传统的投资组合模型不同的是,该模型中投资组合的决策变量是交易手数(整数),其最优化模型是一个非线性整数规划问题.为此本文提出了一个基于拉格朗日松弛和连续松弛的混合分枝定界算法,为测试算法的有效性,我们分别采用美国股票市场真实数据和随机产生的数据,数值结果表明该算法是有效的.

We consider multi-factor pertfolio selection model with concave transaction cost. This discrete portfolio model is of integer quadratic programming problems. The separable structure of the model is exploited by using Lagrangian relaxation and dual search. A new branch-and bound algorithm based on the Lagrangian dual relaxation and continuous relaxation is then proposed. Computational experiments are carried out with data from real-world stock market and randomly generated.