Stock market prediction using machine learning techniques

Mehak Usmani; Syed Hasan Adil; Kamran Raza; Syed Saad Azhar Ali

doi:10.1109/ICCOINS.2016.7783235

Stock market prediction using machine learning techniques

Mehak Usmani
, Syed Hasan Adil
, Kamran Raza
, Syed Saad Azhar Ali

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

124 Scopus citations

Abstract

The main objective of this research is to predict the market performance of Karachi Stock Exchange (KSE) on day closing using different machine learning techniques. The prediction model uses different attributes as an input and predicts market as Positive & Negative. The attributes used in the model includes Oil rates, Gold & Silver rates, Interest rate, Foreign Exchange (FEX) rate, NEWS and social media feed. The old statistical techniques including Simple Moving Average (SMA) and Autoregressive Integrated Moving Average (ARIMA) are also used as input. The machine learning techniques including Single Layer Perceptron (SLP), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and Support Vector Machine (SVM) are compared. All these attributes are studied separately also. The algorithm MLP performed best as compared to other techniques. The oil rate attribute was found to be most relevant to market performance. The results suggest that performance of KSE-100 index can be predicted with machine learning techniques.

Original language	English
Title of host publication	2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	322-327
Number of pages	6
ISBN (Electronic)	9781509051342
DOIs	https://doi.org/10.1109/ICCOINS.2016.7783235
State	Published - 14 Dec 2016
Externally published	Yes
Event	3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Kuala Lumpur, Malaysia Duration: 15 Aug 2016 → 17 Aug 2016

Publication series

Name	2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings

Conference

Conference	3rd International Conference on Computer and Information Sciences, ICCOINS 2016
Country/Territory	Malaysia
City	Kuala Lumpur
Period	15/08/16 → 17/08/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

KSE-100 Index
Neural Networks
Stock Prediction
Support Vector Machine

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment
Environmental Engineering
Computer Science Applications
Information Systems

Access to Document

10.1109/ICCOINS.2016.7783235

Cite this

Usmani, M., Adil, S. H., Raza, K., & Ali, S. S. A. (2016). Stock market prediction using machine learning techniques. In 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings (pp. 322-327). Article 7783235 (2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCOINS.2016.7783235

Usmani, Mehak ; Adil, Syed Hasan ; Raza, Kamran et al. / Stock market prediction using machine learning techniques. 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 322-327 (2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings).

@inproceedings{43acf538d6214ff795d225bab75bdb7c,

title = "Stock market prediction using machine learning techniques",

abstract = "The main objective of this research is to predict the market performance of Karachi Stock Exchange (KSE) on day closing using different machine learning techniques. The prediction model uses different attributes as an input and predicts market as Positive \& Negative. The attributes used in the model includes Oil rates, Gold \& Silver rates, Interest rate, Foreign Exchange (FEX) rate, NEWS and social media feed. The old statistical techniques including Simple Moving Average (SMA) and Autoregressive Integrated Moving Average (ARIMA) are also used as input. The machine learning techniques including Single Layer Perceptron (SLP), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and Support Vector Machine (SVM) are compared. All these attributes are studied separately also. The algorithm MLP performed best as compared to other techniques. The oil rate attribute was found to be most relevant to market performance. The results suggest that performance of KSE-100 index can be predicted with machine learning techniques.",

keywords = "KSE-100 Index, Neural Networks, Stock Prediction, Support Vector Machine",

author = "Mehak Usmani and Adil, \{Syed Hasan\} and Kamran Raza and Ali, \{Syed Saad Azhar\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 ; Conference date: 15-08-2016 Through 17-08-2016",

year = "2016",

month = dec,

day = "14",

doi = "10.1109/ICCOINS.2016.7783235",

language = "English",

series = "2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings",

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

pages = "322--327",

booktitle = "2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings",

address = "United States",

}

Usmani, M, Adil, SH, Raza, K & Ali, SSA 2016, Stock market prediction using machine learning techniques. in 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings., 7783235, 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 322-327, 3rd International Conference on Computer and Information Sciences, ICCOINS 2016, Kuala Lumpur, Malaysia, 15/08/16. https://doi.org/10.1109/ICCOINS.2016.7783235

Stock market prediction using machine learning techniques. / Usmani, Mehak; Adil, Syed Hasan; Raza, Kamran et al.
2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 322-327 7783235 (2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings).

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

TY - GEN

T1 - Stock market prediction using machine learning techniques

AU - Usmani, Mehak

AU - Adil, Syed Hasan

AU - Raza, Kamran

AU - Ali, Syed Saad Azhar

PY - 2016/12/14

Y1 - 2016/12/14

N2 - The main objective of this research is to predict the market performance of Karachi Stock Exchange (KSE) on day closing using different machine learning techniques. The prediction model uses different attributes as an input and predicts market as Positive & Negative. The attributes used in the model includes Oil rates, Gold & Silver rates, Interest rate, Foreign Exchange (FEX) rate, NEWS and social media feed. The old statistical techniques including Simple Moving Average (SMA) and Autoregressive Integrated Moving Average (ARIMA) are also used as input. The machine learning techniques including Single Layer Perceptron (SLP), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and Support Vector Machine (SVM) are compared. All these attributes are studied separately also. The algorithm MLP performed best as compared to other techniques. The oil rate attribute was found to be most relevant to market performance. The results suggest that performance of KSE-100 index can be predicted with machine learning techniques.

AB - The main objective of this research is to predict the market performance of Karachi Stock Exchange (KSE) on day closing using different machine learning techniques. The prediction model uses different attributes as an input and predicts market as Positive & Negative. The attributes used in the model includes Oil rates, Gold & Silver rates, Interest rate, Foreign Exchange (FEX) rate, NEWS and social media feed. The old statistical techniques including Simple Moving Average (SMA) and Autoregressive Integrated Moving Average (ARIMA) are also used as input. The machine learning techniques including Single Layer Perceptron (SLP), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and Support Vector Machine (SVM) are compared. All these attributes are studied separately also. The algorithm MLP performed best as compared to other techniques. The oil rate attribute was found to be most relevant to market performance. The results suggest that performance of KSE-100 index can be predicted with machine learning techniques.

KW - KSE-100 Index

KW - Neural Networks

KW - Stock Prediction

KW - Support Vector Machine

UR - https://www.scopus.com/pages/publications/85010430957

U2 - 10.1109/ICCOINS.2016.7783235

DO - 10.1109/ICCOINS.2016.7783235

M3 - Conference contribution

AN - SCOPUS:85010430957

T3 - 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings

SP - 322

EP - 327

BT - 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Computer and Information Sciences, ICCOINS 2016

Y2 - 15 August 2016 through 17 August 2016

ER -

Usmani M, Adil SH, Raza K, Ali SSA. Stock market prediction using machine learning techniques. In 2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 322-327. 7783235. (2016 3rd International Conference on Computer and Information Sciences, ICCOINS 2016 - Proceedings). doi: 10.1109/ICCOINS.2016.7783235

Stock market prediction using machine learning techniques

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this