An experimental study on diversification in portfolio optimization

作者：

Highlights：

• An experimental study with eleven diversification and mean–variance strategies and thirty datasets.

• Equally-weighted models got the worst results for all experimental metrics except for Stability Index.

• A novel data-driven method to determine the optimal value of the hyper-parameters is proposed.

摘要

•An experimental study with eleven diversification and mean–variance strategies and thirty datasets.•Equally-weighted models got the worst results for all experimental metrics except for Stability Index.•A novel data-driven method to determine the optimal value of the hyper-parameters is proposed.

论文关键词：Mean–variance portfolio,Diversification strategies,1/N portfolio,Hyper-parameter optimization,Out-of-sample performance

论文评审过程：Received 21 February 2021, Revised 12 May 2021, Accepted 12 May 2021, Available online 14 May 2021, Version of Record 17 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115203