Transformer-based attention network for stock movement prediction

作者：

Highlights：

• The stock market is a time series problem, leading to temporal dependence.

• A small-sample feature engineering network framework is proposed.

• The fusion of the Transformer and various attention mechanisms is introduced.

• Transformer model is used to extract deep features.

摘要

•The stock market is a time series problem, leading to temporal dependence.•A small-sample feature engineering network framework is proposed.•The fusion of the Transformer and various attention mechanisms is introduced.•Transformer model is used to extract deep features.

论文关键词：Stock movement prediction,Deep learning,Transformer,Attention

论文评审过程：Received 29 November 2020, Revised 1 April 2022, Accepted 10 April 2022, Available online 21 April 2022, Version of Record 27 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117239