Home > Research > Publications & Outputs > Developing an approach to evaluate stocks by fo...

Links

Text available via DOI:

View graph of relations

Developing an approach to evaluate stocks by forecasting effective features with data mining methods

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Developing an approach to evaluate stocks by forecasting effective features with data mining methods. / Barak, Sasan; Modarres, Mohammad.

In: Expert Systems with Applications, Vol. 42, No. 3, 15.02.2015, p. 1325-1339.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Barak, S & Modarres, M 2015, 'Developing an approach to evaluate stocks by forecasting effective features with data mining methods', Expert Systems with Applications, vol. 42, no. 3, pp. 1325-1339. https://doi.org/10.1016/j.eswa.2014.09.026

APA

Vancouver

Author

Barak, Sasan ; Modarres, Mohammad. / Developing an approach to evaluate stocks by forecasting effective features with data mining methods. In: Expert Systems with Applications. 2015 ; Vol. 42, No. 3. pp. 1325-1339.

Bibtex

@article{f5a7c5cd507945e4a09c5e2f5aa103be,
title = "Developing an approach to evaluate stocks by forecasting effective features with data mining methods",
abstract = "In this research, a novel approach is developed to predict stocks return and risks. In this three-stage method, through a comprehensive investigation all possible features which can be effective on stocks risk and return are identified. Then, in the next stage risk and return are predicted by applying data mining techniques for the given features. Finally, we develop a hybrid algorithm, on the basis of filter and function-based clustering; the important features in risk and return prediction are selected then risk and return re-predicted. The results show that the proposed hybrid model is a proper tool for effective feature selection and these features are good indicators for the prediction of risk and return. To illustrate the approach as well as to train data and test, we apply it to Tehran Stock Exchange (TSE) data from 2002 to 2011.",
keywords = "Stock market, Data mining, Classification algorithm, Feature selection, Function-based clustering method",
author = "Sasan Barak and Mohammad Modarres",
year = "2015",
month = feb,
day = "15",
doi = "10.1016/j.eswa.2014.09.026",
language = "English",
volume = "42",
pages = "1325--1339",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Ltd",
number = "3",

}

RIS

TY - JOUR

T1 - Developing an approach to evaluate stocks by forecasting effective features with data mining methods

AU - Barak, Sasan

AU - Modarres, Mohammad

PY - 2015/2/15

Y1 - 2015/2/15

N2 - In this research, a novel approach is developed to predict stocks return and risks. In this three-stage method, through a comprehensive investigation all possible features which can be effective on stocks risk and return are identified. Then, in the next stage risk and return are predicted by applying data mining techniques for the given features. Finally, we develop a hybrid algorithm, on the basis of filter and function-based clustering; the important features in risk and return prediction are selected then risk and return re-predicted. The results show that the proposed hybrid model is a proper tool for effective feature selection and these features are good indicators for the prediction of risk and return. To illustrate the approach as well as to train data and test, we apply it to Tehran Stock Exchange (TSE) data from 2002 to 2011.

AB - In this research, a novel approach is developed to predict stocks return and risks. In this three-stage method, through a comprehensive investigation all possible features which can be effective on stocks risk and return are identified. Then, in the next stage risk and return are predicted by applying data mining techniques for the given features. Finally, we develop a hybrid algorithm, on the basis of filter and function-based clustering; the important features in risk and return prediction are selected then risk and return re-predicted. The results show that the proposed hybrid model is a proper tool for effective feature selection and these features are good indicators for the prediction of risk and return. To illustrate the approach as well as to train data and test, we apply it to Tehran Stock Exchange (TSE) data from 2002 to 2011.

KW - Stock market

KW - Data mining

KW - Classification algorithm

KW - Feature selection

KW - Function-based clustering method

U2 - 10.1016/j.eswa.2014.09.026

DO - 10.1016/j.eswa.2014.09.026

M3 - Journal article

VL - 42

SP - 1325

EP - 1339

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3

ER -