Effect of dimensionality reduction on stock selection with cluster analysis in different market situations
作者：
Highlights：
• Dimensionality reduction hardly improves the Sharpe ratio of stock selection in sideways.
• The advantage of dimensionality reduction is mainly reflected in trend situations.
• A stock-selection rotation strategy with and without dimensionality reduction is proposed.
• The Sharpe ratio of the rotation strategy is higher than that of benchmark strategies.
摘要
•Dimensionality reduction hardly improves the Sharpe ratio of stock selection in sideways.•The advantage of dimensionality reduction is mainly reflected in trend situations.•A stock-selection rotation strategy with and without dimensionality reduction is proposed.•The Sharpe ratio of the rotation strategy is higher than that of benchmark strategies.
论文关键词：Stock selection,Dimensionality reduction,Market situation,Rotation strategy,Deep learning
论文评审过程：Received 14 February 2019, Revised 16 January 2020, Accepted 19 January 2020, Available online 20 January 2020, Version of Record 28 January 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113226
