Forecasting daily stock trend using multi-filter feature selection and deep learning

作者：

Highlights：

• Forty-four financial indicators are computed from historical data of 88 stocks.

• A correlation-based multi-filter feature selection selects a more optimal feature set.

• A deep generative model is used for predicting future stock price trends.

• The results demonstrate that feature selection positively effect performance of prediction model.

摘要

•Forty-four financial indicators are computed from historical data of 88 stocks.•A correlation-based multi-filter feature selection selects a more optimal feature set.•A deep generative model is used for predicting future stock price trends.•The results demonstrate that feature selection positively effect performance of prediction model.

论文关键词：Stock trend prediction,Feature selection,Deep learning,Machine learning

论文评审过程：Received 30 May 2020, Revised 5 September 2020, Accepted 2 December 2020, Available online 5 December 2020, Version of Record 9 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114444