Deep learning with multiple scale attention and direction regularization for asset price prediction

作者：

Highlights：

• We design a scale attention deep learning model for asset price prediction.

• Our model learns the movement direction during forecasting the future stock price.

• Our model exceeds benchmarks in forecasting future price and movement direction.

摘要

•We design a scale attention deep learning model for asset price prediction.•Our model learns the movement direction during forecasting the future stock price.•Our model exceeds benchmarks in forecasting future price and movement direction.

论文关键词：Asset price prediction,Deep representations,Scale attention mechanism,Direction priori information

论文评审过程：Received 11 February 2020, Revised 16 July 2021, Accepted 21 August 2021, Available online 5 September 2021, Version of Record 9 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115796