Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU)

Khaled A. Althelaya; El Sayed M. El-Alfy; Salahadin Mohammed

doi:10.1109/NCG.2018.8593076

Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU)

Khaled A. Althelaya, El Sayed M. El-Alfy, Salahadin Mohammed

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

86 Scopus citations

Abstract

Deep learning has recently received growing interest and attention. It has been successfully applied to many fields. Stock market time-series forecasting is one the most challenging problems for a variety of learning methodologies. In this paper, we studied the integration of deep learning methodologies into stock market forecasting. We evaluated and compared a number of variants of Deep Recurrent Neural Network based on LSTM and GRU. Both bidirectional and unidirectional stacked architectures with multivariate inputs were employed to perform short- and long-term forecasting. The deep learning architectures were also compared to shallow neural networks using S P500 index historical data. It has been noticed that a stacked LSTM architecture has demonstrated the highest forecasting performance for both short- and long-term.

Original language	English
Title of host publication	21st Saudi Computer Society National Computer Conference, NCC 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538641095
DOIs	https://doi.org/10.1109/NCG.2018.8593076
State	Published - 27 Dec 2018

Publication series

Name	21st Saudi Computer Society National Computer Conference, NCC 2018

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Information Systems
Health Informatics

Access to Document

10.1109/NCG.2018.8593076

Cite this

Althelaya, K. A., El-Alfy, E. S. M., & Mohammed, S. (2018). Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU). In 21st Saudi Computer Society National Computer Conference, NCC 2018 Article 8593076 (21st Saudi Computer Society National Computer Conference, NCC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NCG.2018.8593076

@inproceedings{dd25c7c8efad41be82753c80fe551dee,

title = "Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU)",

abstract = "Deep learning has recently received growing interest and attention. It has been successfully applied to many fields. Stock market time-series forecasting is one the most challenging problems for a variety of learning methodologies. In this paper, we studied the integration of deep learning methodologies into stock market forecasting. We evaluated and compared a number of variants of Deep Recurrent Neural Network based on LSTM and GRU. Both bidirectional and unidirectional stacked architectures with multivariate inputs were employed to perform short- and long-term forecasting. The deep learning architectures were also compared to shallow neural networks using S P500 index historical data. It has been noticed that a stacked LSTM architecture has demonstrated the highest forecasting performance for both short- and long-term.",

author = "Althelaya, \{Khaled A.\} and El-Alfy, \{El Sayed M.\} and Salahadin Mohammed",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.",

year = "2018",

month = dec,

day = "27",

doi = "10.1109/NCG.2018.8593076",

language = "English",

series = "21st Saudi Computer Society National Computer Conference, NCC 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "21st Saudi Computer Society National Computer Conference, NCC 2018",

address = "United States",

}

Althelaya, KA, El-Alfy, ESM & Mohammed, S 2018, Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU). in 21st Saudi Computer Society National Computer Conference, NCC 2018., 8593076, 21st Saudi Computer Society National Computer Conference, NCC 2018, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/NCG.2018.8593076

Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU). / Althelaya, Khaled A.; El-Alfy, El Sayed M.; Mohammed, Salahadin.
21st Saudi Computer Society National Computer Conference, NCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8593076 (21st Saudi Computer Society National Computer Conference, NCC 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU)

AU - Althelaya, Khaled A.

AU - El-Alfy, El Sayed M.

AU - Mohammed, Salahadin

PY - 2018/12/27

Y1 - 2018/12/27

N2 - Deep learning has recently received growing interest and attention. It has been successfully applied to many fields. Stock market time-series forecasting is one the most challenging problems for a variety of learning methodologies. In this paper, we studied the integration of deep learning methodologies into stock market forecasting. We evaluated and compared a number of variants of Deep Recurrent Neural Network based on LSTM and GRU. Both bidirectional and unidirectional stacked architectures with multivariate inputs were employed to perform short- and long-term forecasting. The deep learning architectures were also compared to shallow neural networks using S P500 index historical data. It has been noticed that a stacked LSTM architecture has demonstrated the highest forecasting performance for both short- and long-term.

AB - Deep learning has recently received growing interest and attention. It has been successfully applied to many fields. Stock market time-series forecasting is one the most challenging problems for a variety of learning methodologies. In this paper, we studied the integration of deep learning methodologies into stock market forecasting. We evaluated and compared a number of variants of Deep Recurrent Neural Network based on LSTM and GRU. Both bidirectional and unidirectional stacked architectures with multivariate inputs were employed to perform short- and long-term forecasting. The deep learning architectures were also compared to shallow neural networks using S P500 index historical data. It has been noticed that a stacked LSTM architecture has demonstrated the highest forecasting performance for both short- and long-term.

UR - https://www.scopus.com/pages/publications/85061485605

U2 - 10.1109/NCG.2018.8593076

DO - 10.1109/NCG.2018.8593076

M3 - Conference contribution

AN - SCOPUS:85061485605

T3 - 21st Saudi Computer Society National Computer Conference, NCC 2018

BT - 21st Saudi Computer Society National Computer Conference, NCC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Althelaya KA, El-Alfy ESM, Mohammed S. Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU). In 21st Saudi Computer Society National Computer Conference, NCC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8593076. (21st Saudi Computer Society National Computer Conference, NCC 2018). doi: 10.1109/NCG.2018.8593076

Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU)

Abstract

Publication series

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this