Predicting Stock Price Movements Based on Different Categories of News Articles

Yauheniya Shynkevich, TM McGinnity, SA Coleman, Ammar Belatreche

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Publications of financial news articles impact the decisions made by investors and, therefore, change the market state. It makes them an important source of data for financial predictions. Forecasting models based on information derived from news have been recently developed and researched. However, the advantages of combining different categories of news articles have not been investigated. This research paper studies how the results of financial forecasting can be improved when news articles with different levels of relevance to the target stock are used simultaneously. Integration of information extracted from five categories of news articles partitioned by sectors and industries is performed using the multiple kernel learning technique for predicting price movements. News articles are divided into these five categories based on their relevance to a targeted stock, its sub industry, industry, group industry and sector while separate kernels are employed to analyze each one. The experimental results show that the simultaneous usage of five news categories improves the prediction performance in comparison with methods based on a lower number of news categories.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages703-710
Number of pages8
DOIs
Publication statusPublished - 6 Dec 2015
Event2015 IEEE Symposium Series on Computational Intelligence - Cape Town
Duration: 6 Dec 2015 → …

Conference

Conference2015 IEEE Symposium Series on Computational Intelligence
Period6/12/15 → …

Fingerprint

Industry

Keywords

  • prediction
  • stock

Cite this

Shynkevich, Yauheniya ; McGinnity, TM ; Coleman, SA ; Belatreche, Ammar. / Predicting Stock Price Movements Based on Different Categories of News Articles. Unknown Host Publication. 2015. pp. 703-710
@inproceedings{8d27a753fb164fa796d9bcd9c89e36ac,
title = "Predicting Stock Price Movements Based on Different Categories of News Articles",
abstract = "Publications of financial news articles impact the decisions made by investors and, therefore, change the market state. It makes them an important source of data for financial predictions. Forecasting models based on information derived from news have been recently developed and researched. However, the advantages of combining different categories of news articles have not been investigated. This research paper studies how the results of financial forecasting can be improved when news articles with different levels of relevance to the target stock are used simultaneously. Integration of information extracted from five categories of news articles partitioned by sectors and industries is performed using the multiple kernel learning technique for predicting price movements. News articles are divided into these five categories based on their relevance to a targeted stock, its sub industry, industry, group industry and sector while separate kernels are employed to analyze each one. The experimental results show that the simultaneous usage of five news categories improves the prediction performance in comparison with methods based on a lower number of news categories.",
keywords = "prediction, stock",
author = "Yauheniya Shynkevich and TM McGinnity and SA Coleman and Ammar Belatreche",
year = "2015",
month = "12",
day = "6",
doi = "10.1109/SSCI.2015.107",
language = "English",
isbn = "978-1-4799-7560-0",
pages = "703--710",
booktitle = "Unknown Host Publication",

}

Shynkevich, Y, McGinnity, TM, Coleman, SA & Belatreche, A 2015, Predicting Stock Price Movements Based on Different Categories of News Articles. in Unknown Host Publication. pp. 703-710, 2015 IEEE Symposium Series on Computational Intelligence, 6/12/15. https://doi.org/10.1109/SSCI.2015.107

Predicting Stock Price Movements Based on Different Categories of News Articles. / Shynkevich, Yauheniya; McGinnity, TM; Coleman, SA; Belatreche, Ammar.

Unknown Host Publication. 2015. p. 703-710.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Predicting Stock Price Movements Based on Different Categories of News Articles

AU - Shynkevich, Yauheniya

AU - McGinnity, TM

AU - Coleman, SA

AU - Belatreche, Ammar

PY - 2015/12/6

Y1 - 2015/12/6

N2 - Publications of financial news articles impact the decisions made by investors and, therefore, change the market state. It makes them an important source of data for financial predictions. Forecasting models based on information derived from news have been recently developed and researched. However, the advantages of combining different categories of news articles have not been investigated. This research paper studies how the results of financial forecasting can be improved when news articles with different levels of relevance to the target stock are used simultaneously. Integration of information extracted from five categories of news articles partitioned by sectors and industries is performed using the multiple kernel learning technique for predicting price movements. News articles are divided into these five categories based on their relevance to a targeted stock, its sub industry, industry, group industry and sector while separate kernels are employed to analyze each one. The experimental results show that the simultaneous usage of five news categories improves the prediction performance in comparison with methods based on a lower number of news categories.

AB - Publications of financial news articles impact the decisions made by investors and, therefore, change the market state. It makes them an important source of data for financial predictions. Forecasting models based on information derived from news have been recently developed and researched. However, the advantages of combining different categories of news articles have not been investigated. This research paper studies how the results of financial forecasting can be improved when news articles with different levels of relevance to the target stock are used simultaneously. Integration of information extracted from five categories of news articles partitioned by sectors and industries is performed using the multiple kernel learning technique for predicting price movements. News articles are divided into these five categories based on their relevance to a targeted stock, its sub industry, industry, group industry and sector while separate kernels are employed to analyze each one. The experimental results show that the simultaneous usage of five news categories improves the prediction performance in comparison with methods based on a lower number of news categories.

KW - prediction

KW - stock

U2 - 10.1109/SSCI.2015.107

DO - 10.1109/SSCI.2015.107

M3 - Conference contribution

SN - 978-1-4799-7560-0

SP - 703

EP - 710

BT - Unknown Host Publication

ER -