Enhancing financial decision-making using social behavior modeling

Ruoqian Liu*, Ankit Agrawal, Wei Keng Liao, Alok Choudhary

*Corresponding author for this work

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

1 Scopus citations

Abstract

Financial trading is a social activity that involves every par- ticipant's decision making. Meanwhile, people's online be- havior collectively creates the public emotion which affects investors' reactions and hence market movements. This pro- cess can be modeled by connecting online social behavior and future trading behavior to better understand mechanisms of the stock movement so as to assist financial decision making. In this paper, we investigate the query information of financially related Wikipedia pages, and show that early signs of trading volume movements can be detected which expose financial risks. We embed this information into a classic pairs trading strategy acting on a large portfolio of stocks. Over 23% profits are seen when testing on the year of 2013 and 20% comes from the inclusion of online social data.

Original languageEnglish (US)
Title of host publicationProceedings of the 8th Workshop on Social Network Mining and Analysis, SNAKDD 2014
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)1595930361, 9781450331920
DOIs
StatePublished - Aug 24 2014
Event8th Workshop on Social Network Mining and Analysis, SNAKDD 2014 - New York, United States
Duration: Aug 24 2014Aug 27 2014

Publication series

NameProceedings of the 8th Workshop on Social Network Mining and Analysis, SNAKDD 2014

Other

Other8th Workshop on Social Network Mining and Analysis, SNAKDD 2014
Country/TerritoryUnited States
CityNew York
Period8/24/148/27/14

Keywords

  • Algorithmic trading
  • Social activity modeling
  • Wikipedia

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Social Psychology

Fingerprint

Dive into the research topics of 'Enhancing financial decision-making using social behavior modeling'. Together they form a unique fingerprint.

Cite this