How to make machine select stocks like fund managers? Use scoring and screening model

作者：

Highlights：

• Multisource data are fused for stock selection.

• The fusion model has a great performance for the screening ability.

• Seq2Seq model and t-merge factor model are built as scoring models.

• The discrimination model and media sentimental model are screening models.

• Models are analyzed and validated on China’s stock market.

摘要

•Multisource data are fused for stock selection.•The fusion model has a great performance for the screening ability.•Seq2Seq model and t-merge factor model are built as scoring models.•The discrimination model and media sentimental model are screening models.•Models are analyzed and validated on China’s stock market.

论文关键词：Stock selection,Model fusion,Stock screening,Factor modeling,Deep learning

论文评审过程：Received 2 November 2021, Revised 25 January 2022, Accepted 29 January 2022, Available online 17 February 2022, Version of Record 23 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116629