Application of combined arma-neural network models to predict stock prices

Mohammad Umair Yaqub; Mohammad Saad Al-Ahmadi

doi:10.1145/2955129.2955171

Application of combined arma-neural network models to predict stock prices

Mohammad Umair Yaqub, Mohammad Saad Al-Ahmadi

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

6 Scopus citations

Abstract

Predicting the prices of stocks is a very important field of research nowadays. Many different types of models have already been implemented. Two types of techniques include ARMA models and Neural Networks. In this work, ARMA models, along with two types of Neural Networks (Back Propagation) and Multi-Layer Perceptron (MLP) have been used. Furthermore, the two neural networks were combined with ARMA models (individually) in order to generate the best forecasted prices. The two indexes used for forecasting are the Dow Jones Industrial Average (DJI) and the Saudi Stock Exchange Tadawul (TASI). 800 values were used to predict the future 200 values. It was found out that for such large number of predictions, MLP yields the best results, which are drastically improved when combined with ARMA forecasting.

Original language	English
Title of host publication	Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016
Publisher	Association for Computing Machinery
ISBN (Print)	9781450341295
DOIs	https://doi.org/10.1145/2955129.2955171
State	Published - 15 Aug 2016

Publication series

Name	ACM International Conference Proceeding Series

Bibliographical note

Publisher Copyright:
© 2016 ACM.

Keywords

Artificial intelligence (AI)
Auto-regressive moving average (ARMA)
Back-propagation neural network (BPNN)
Multi-layer perceptron neural network (MLP-NN)
Stock forecasting

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/2955129.2955171

Cite this

Yaqub, M. U., & Al-Ahmadi, M. S. (2016). Application of combined arma-neural network models to predict stock prices. In Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016 Article a40 (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/2955129.2955171

@inproceedings{231b99b112fd4f1ca0c7debd4b9cd933,

title = "Application of combined arma-neural network models to predict stock prices",

abstract = "Predicting the prices of stocks is a very important field of research nowadays. Many different types of models have already been implemented. Two types of techniques include ARMA models and Neural Networks. In this work, ARMA models, along with two types of Neural Networks (Back Propagation) and Multi-Layer Perceptron (MLP) have been used. Furthermore, the two neural networks were combined with ARMA models (individually) in order to generate the best forecasted prices. The two indexes used for forecasting are the Dow Jones Industrial Average (DJI) and the Saudi Stock Exchange Tadawul (TASI). 800 values were used to predict the future 200 values. It was found out that for such large number of predictions, MLP yields the best results, which are drastically improved when combined with ARMA forecasting.",

keywords = "Artificial intelligence (AI), Auto-regressive moving average (ARMA), Back-propagation neural network (BPNN), Multi-layer perceptron neural network (MLP-NN), Stock forecasting",

author = "Yaqub, \{Mohammad Umair\} and Al-Ahmadi, \{Mohammad Saad\}",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.",

year = "2016",

month = aug,

day = "15",

doi = "10.1145/2955129.2955171",

language = "English",

isbn = "9781450341295",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016",

}

Yaqub, MU & Al-Ahmadi, MS 2016, Application of combined arma-neural network models to predict stock prices. in Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016., a40, ACM International Conference Proceeding Series, Association for Computing Machinery. https://doi.org/10.1145/2955129.2955171

Application of combined arma-neural network models to predict stock prices. / Yaqub, Mohammad Umair; Al-Ahmadi, Mohammad Saad.
Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016. Association for Computing Machinery, 2016. a40 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Application of combined arma-neural network models to predict stock prices

AU - Yaqub, Mohammad Umair

AU - Al-Ahmadi, Mohammad Saad

PY - 2016/8/15

Y1 - 2016/8/15

N2 - Predicting the prices of stocks is a very important field of research nowadays. Many different types of models have already been implemented. Two types of techniques include ARMA models and Neural Networks. In this work, ARMA models, along with two types of Neural Networks (Back Propagation) and Multi-Layer Perceptron (MLP) have been used. Furthermore, the two neural networks were combined with ARMA models (individually) in order to generate the best forecasted prices. The two indexes used for forecasting are the Dow Jones Industrial Average (DJI) and the Saudi Stock Exchange Tadawul (TASI). 800 values were used to predict the future 200 values. It was found out that for such large number of predictions, MLP yields the best results, which are drastically improved when combined with ARMA forecasting.

AB - Predicting the prices of stocks is a very important field of research nowadays. Many different types of models have already been implemented. Two types of techniques include ARMA models and Neural Networks. In this work, ARMA models, along with two types of Neural Networks (Back Propagation) and Multi-Layer Perceptron (MLP) have been used. Furthermore, the two neural networks were combined with ARMA models (individually) in order to generate the best forecasted prices. The two indexes used for forecasting are the Dow Jones Industrial Average (DJI) and the Saudi Stock Exchange Tadawul (TASI). 800 values were used to predict the future 200 values. It was found out that for such large number of predictions, MLP yields the best results, which are drastically improved when combined with ARMA forecasting.

KW - Artificial intelligence (AI)

KW - Auto-regressive moving average (ARMA)

KW - Back-propagation neural network (BPNN)

KW - Multi-layer perceptron neural network (MLP-NN)

KW - Stock forecasting

UR - https://www.scopus.com/pages/publications/85054155952

U2 - 10.1145/2955129.2955171

DO - 10.1145/2955129.2955171

M3 - Conference contribution

AN - SCOPUS:85054155952

SN - 9781450341295

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016

PB - Association for Computing Machinery

ER -

Yaqub MU, Al-Ahmadi MS. Application of combined arma-neural network models to predict stock prices. In Proceedings of the 3rd Multidisciplinary International Social Networks Conference, SocialInformatics 2016, Data Science 2016, MISNC, SI, DS 2016. Association for Computing Machinery. 2016. a40. (ACM International Conference Proceeding Series). doi: 10.1145/2955129.2955171

Application of combined arma-neural network models to predict stock prices

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this