Diversification improvements through news article co-occurrences

John Robert Yaros, Tomasz Imielinski

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

Abstract

Intuition suggests that a set of companies mentioned in the same news article are more likely to be related than unrelated. For instance, an article discussing a retailer would more probably mention its competitors or supply chain partners than mention other companies with no economic connection. Correspondingly, we consider using news article co-occurrences as a means to determine company relatedness. We show that companies mentioned together frequently are more likely to have higher future stock-return correlation, and consider using this data source as a means to achieve portfolio diversification by avoiding having pairs of related companies in the portfolio. We find this approach reduces risk and can be used to improve standard approaches to diversification that use expert-defined industry taxonomies, seeking to avoid portfolio concentration in any given economic sector.

Original languageEnglish (US)
Title of host publication2014 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, CIFEr Proceedings
EditorsAntoaneta Serguieva, Dietmar Maringer, Vasile Palade, Rui Jorge Almeida
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages130-137
Number of pages8
ISBN (Electronic)9781479923809
DOIs
StatePublished - Oct 14 2014
Event2014 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, CIFEr 2014 - London, United Kingdom
Duration: Mar 27 2014Mar 28 2014

Publication series

NameIEEE/IAFE Conference on Computational Intelligence for Financial Engineering, Proceedings (CIFEr)

Other

Other2014 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, CIFEr 2014
Country/TerritoryUnited Kingdom
CityLondon
Period3/27/143/28/14

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Artificial Intelligence
  • Software
  • Applied Mathematics
  • Finance

Fingerprint

Dive into the research topics of 'Diversification improvements through news article co-occurrences'. Together they form a unique fingerprint.

Cite this