Does summarization help stock prediction? A news impact analysis

Xiaodong LI, Haoran XIE*, Yangqiu SONG, Shanfeng ZHU, Qing LI, Fu Lee WANG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)

30 Citations (Scopus)

Abstract

The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.

Original languageEnglish
Pages (from-to)26-34
Number of pages9
JournalIEEE Intelligent Systems
Volume30
Issue number3
Early online date12 Jan 2015
DOIs
Publication statusPublished - May 2015
Externally publishedYes

Fingerprint

Electronic data interchange
Testing
Experiments

Keywords

  • intelligent systems
  • news summarization
  • predictive analytics
  • Predictive models
  • stock prediction

Cite this

LI, Xiaodong ; XIE, Haoran ; SONG, Yangqiu ; ZHU, Shanfeng ; LI, Qing ; WANG, Fu Lee. / Does summarization help stock prediction? A news impact analysis. In: IEEE Intelligent Systems. 2015 ; Vol. 30, No. 3. pp. 26-34.
@article{6e723f286b87483dbed8a062caf955ee,
title = "Does summarization help stock prediction? A news impact analysis",
abstract = "The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.",
keywords = "intelligent systems, news summarization, predictive analytics, Predictive models, stock prediction",
author = "Xiaodong LI and Haoran XIE and Yangqiu SONG and Shanfeng ZHU and Qing LI and WANG, {Fu Lee}",
year = "2015",
month = "5",
doi = "10.1109/MIS.2015.1",
language = "English",
volume = "30",
pages = "26--34",
journal = "IEEE Intelligent Systems",
issn = "1541-1672",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Does summarization help stock prediction? A news impact analysis. / LI, Xiaodong; XIE, Haoran; SONG, Yangqiu; ZHU, Shanfeng; LI, Qing; WANG, Fu Lee.

In: IEEE Intelligent Systems, Vol. 30, No. 3, 05.2015, p. 26-34.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Does summarization help stock prediction? A news impact analysis

AU - LI, Xiaodong

AU - XIE, Haoran

AU - SONG, Yangqiu

AU - ZHU, Shanfeng

AU - LI, Qing

AU - WANG, Fu Lee

PY - 2015/5

Y1 - 2015/5

N2 - The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.

AB - The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.

KW - intelligent systems

KW - news summarization

KW - predictive analytics

KW - Predictive models

KW - stock prediction

UR - http://www.scopus.com/inward/record.url?scp=84930662743&partnerID=8YFLogxK

U2 - 10.1109/MIS.2015.1

DO - 10.1109/MIS.2015.1

M3 - Journal Article (refereed)

AN - SCOPUS:84930662743

VL - 30

SP - 26

EP - 34

JO - IEEE Intelligent Systems

JF - IEEE Intelligent Systems

SN - 1541-1672

IS - 3

ER -