Forecasting Movements of Health-Care Stock Prices Based on Different Categories of News Articles using Multiple Kernel Learning

Yauheniya Shynkevich, Martin McGinnity, Sonya Coleman, Ammar Belatreche

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

The market state changes when a new piece of information arrives. It affects decisions made by investors and is considered to be an important data source that can be used for financial forecasting. Recently information derived from news articles has become a part of financial predictive systems. The usage of news articles and their forecasting potential have been extensively researched. However, so far no attempts have been made to utilise different categories of news articles simultaneously. This paper studies how the concurrent, and appropriately weighted, usage of news articles, having different degrees of relevance to the target stock, can improve the performance of financial forecasting and support the decision-making process of investors and traders. Stock price movements are predicted using the multiple kernel learning technique which integrates information extracted from multiple news categories while separate kernels are utilised to analyse each category. News articles are partitioned according to their relevance to the target stock, its sub-industry, industry, group industry and sector. The experiments are run on stocks from the Health Care sector and show that increasing the number of relevant news categories used as data sources for financial forecasting improves the performance of the predictive system in comparison with approaches based on a lower number of categories.
LanguageEnglish
Pages74-83
JournalDecision Support Systems
Volume85
Early online date1 May 2016
DOIs
Publication statusE-pub ahead of print - 1 May 2016

Fingerprint

Health care
Learning
Delivery of Health Care
Industry
Information Storage and Retrieval
Financial Support
Health Care Sector
Decision Making
Cohort Studies
Decision making
Stock prices
News
Kernel
Healthcare
News Articles
Experiments
Financial forecasting
Investors

Keywords

  • Stock price prediction
  • Financial news
  • Text mining
  • Multiple kernel learning
  • Decision support systems

Cite this

@article{7d31dbab641d409984243bcd3873aa2d,
title = "Forecasting Movements of Health-Care Stock Prices Based on Different Categories of News Articles using Multiple Kernel Learning",
abstract = "The market state changes when a new piece of information arrives. It affects decisions made by investors and is considered to be an important data source that can be used for financial forecasting. Recently information derived from news articles has become a part of financial predictive systems. The usage of news articles and their forecasting potential have been extensively researched. However, so far no attempts have been made to utilise different categories of news articles simultaneously. This paper studies how the concurrent, and appropriately weighted, usage of news articles, having different degrees of relevance to the target stock, can improve the performance of financial forecasting and support the decision-making process of investors and traders. Stock price movements are predicted using the multiple kernel learning technique which integrates information extracted from multiple news categories while separate kernels are utilised to analyse each category. News articles are partitioned according to their relevance to the target stock, its sub-industry, industry, group industry and sector. The experiments are run on stocks from the Health Care sector and show that increasing the number of relevant news categories used as data sources for financial forecasting improves the performance of the predictive system in comparison with approaches based on a lower number of categories.",
keywords = "Stock price prediction, Financial news, Text mining, Multiple kernel learning, Decision support systems",
author = "Yauheniya Shynkevich and Martin McGinnity and Sonya Coleman and Ammar Belatreche",
year = "2016",
month = "5",
day = "1",
doi = "10.1016/j.dss.2016.03.001",
language = "English",
volume = "85",
pages = "74--83",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",

}

Forecasting Movements of Health-Care Stock Prices Based on Different Categories of News Articles using Multiple Kernel Learning. / Shynkevich, Yauheniya; McGinnity, Martin; Coleman, Sonya; Belatreche, Ammar.

In: Decision Support Systems, Vol. 85, 01.05.2016, p. 74-83.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Forecasting Movements of Health-Care Stock Prices Based on Different Categories of News Articles using Multiple Kernel Learning

AU - Shynkevich, Yauheniya

AU - McGinnity, Martin

AU - Coleman, Sonya

AU - Belatreche, Ammar

PY - 2016/5/1

Y1 - 2016/5/1

N2 - The market state changes when a new piece of information arrives. It affects decisions made by investors and is considered to be an important data source that can be used for financial forecasting. Recently information derived from news articles has become a part of financial predictive systems. The usage of news articles and their forecasting potential have been extensively researched. However, so far no attempts have been made to utilise different categories of news articles simultaneously. This paper studies how the concurrent, and appropriately weighted, usage of news articles, having different degrees of relevance to the target stock, can improve the performance of financial forecasting and support the decision-making process of investors and traders. Stock price movements are predicted using the multiple kernel learning technique which integrates information extracted from multiple news categories while separate kernels are utilised to analyse each category. News articles are partitioned according to their relevance to the target stock, its sub-industry, industry, group industry and sector. The experiments are run on stocks from the Health Care sector and show that increasing the number of relevant news categories used as data sources for financial forecasting improves the performance of the predictive system in comparison with approaches based on a lower number of categories.

AB - The market state changes when a new piece of information arrives. It affects decisions made by investors and is considered to be an important data source that can be used for financial forecasting. Recently information derived from news articles has become a part of financial predictive systems. The usage of news articles and their forecasting potential have been extensively researched. However, so far no attempts have been made to utilise different categories of news articles simultaneously. This paper studies how the concurrent, and appropriately weighted, usage of news articles, having different degrees of relevance to the target stock, can improve the performance of financial forecasting and support the decision-making process of investors and traders. Stock price movements are predicted using the multiple kernel learning technique which integrates information extracted from multiple news categories while separate kernels are utilised to analyse each category. News articles are partitioned according to their relevance to the target stock, its sub-industry, industry, group industry and sector. The experiments are run on stocks from the Health Care sector and show that increasing the number of relevant news categories used as data sources for financial forecasting improves the performance of the predictive system in comparison with approaches based on a lower number of categories.

KW - Stock price prediction

KW - Financial news

KW - Text mining

KW - Multiple kernel learning

KW - Decision support systems

U2 - 10.1016/j.dss.2016.03.001

DO - 10.1016/j.dss.2016.03.001

M3 - Article

VL - 85

SP - 74

EP - 83

JO - Decision Support Systems

T2 - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

ER -