A new evolutionary algorithm based on MOEA/D for portfolio optimization
Heng Zhang, Yaoyu Zhao, Feng Wang, Anran Zhang, Pengwei Yang, Xiao‐Liang Shen · 2018
The portfolio optimization problem is a multi-objective problem which takes risk and return as optimization objectives. It is complicated in reality with many restrictions which results in an complex pareto front. MOEA/D is a popular multi-objective evolutionary algorithm framework with decomposition method, which has widely been used to solve multi-objective problems. In order to solve portfolio optimization problem with complex pareto front more effectively, we propose a new algorithm named MOEA/D-CP based on MOEA/D, which utilizes a new weight vector generation approach to generate a evenly distributed set of weight vectors. The experimental results show that the MOEA/D-CP performs much better than algorithm based on original MOEA/D.