Modal decomposition-based hybrid model for stock index prediction

作者：

Highlights：

• A novel deep learning hybrid model for stock index prediction is proposed.

• Stock index is decomposed into a series of intrinsic mode functions by CEEMDAN.

• Nonlinear features of a stock index are extracted using deep autoencoder (DAE).

• Long short-term memory (LSTM) networks are used for time series fitting.

• Higher prediction accuracy is achieved compared with existing methods.

摘要

•A novel deep learning hybrid model for stock index prediction is proposed.•Stock index is decomposed into a series of intrinsic mode functions by CEEMDAN.•Nonlinear features of a stock index are extracted using deep autoencoder (DAE).•Long short-term memory (LSTM) networks are used for time series fitting.•Higher prediction accuracy is achieved compared with existing methods.

论文关键词：Stock index prediction,Deep learning hybrid prediction model,Adaptive noise complete ensemble empirical mode decomposition,Deep autoencoder,Long short-term memory

论文评审过程：Received 14 November 2021, Revised 27 January 2022, Accepted 13 April 2022, Available online 22 April 2022, Version of Record 26 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117252