Developing a deep learning framework with two-stage feature selection for multivariate financial time series forecasting

作者：

Highlights：

• Propose a novel feature selection method for dimensionality reduction.

• Develop an improved multi-objective optimization algorithm.

• Establish a forecasting framework based on feature selection and deep learning.

• Experimental results demonstrate the effectiveness of the framework.

摘要

•Propose a novel feature selection method for dimensionality reduction.•Develop an improved multi-objective optimization algorithm.•Establish a forecasting framework based on feature selection and deep learning.•Experimental results demonstrate the effectiveness of the framework.

论文关键词：Deep learning,Multivariate financial time series,Forecasting,Feature selection,Multi-objective optimization

论文评审过程：Received 15 November 2019, Revised 28 December 2019, Accepted 22 January 2020, Available online 24 January 2020, Version of Record 31 January 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113237