A comprehensive survey on deep neural networks for stock market: The need, challenges, and future directions

作者：

Highlights：

• The need of deep neural networks for stock price and trend prediction is discussed.

• CNN, DQN, RNN, LSTM, GRU, ESN, DNN, RBM, and DBN are reviewed for stock prediction.

• An experimental comparison of nine models is carried out and results are analysed.

• The prediction performance of considered models are compared with existing approach.

• The challenges and potential future research directions are also provided.

摘要

•The need of deep neural networks for stock price and trend prediction is discussed.•CNN, DQN, RNN, LSTM, GRU, ESN, DNN, RBM, and DBN are reviewed for stock prediction.•An experimental comparison of nine models is carried out and results are analysed.•The prediction performance of considered models are compared with existing approach.•The challenges and potential future research directions are also provided.

论文关键词：Stock market prediction,Deep neural network,Convolutional neural network,Recurrent neural network,Challenges,Future research directions

论文评审过程：Received 14 October 2020, Revised 31 January 2021, Accepted 25 February 2021, Available online 11 March 2021, Version of Record 9 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114800