Detecting Equity Style Information Within Institutional Media

Cédric Gillain (), Ashwin Ittoo () and Marie Lambert ()
Additional contact information
Cédric Gillain: HEC Liège, Management School of the University of Liège
Ashwin Ittoo: HEC Liège, Management School of the University of Liège
Marie Lambert: HEC Liège, Management School of the University of Liège

A chapter in Essays on Financial Analytics, 2023, pp 131-157 from Springer

Abstract: Abstract This study examines the detection of information related to small and large equity styles. Using a novel database of magazines targeting institutional investors, the institutional media, we compare the performance of dictionary-based and supervised machine learning algorithms (Naïve Bayes and support vector machine). Our three main findings are (1) restricted word lists are the most efficient approach, (2) bigram term frequency matrices are the best weighting scheme for algorithms, and (3) Naïve Bayes exhibits overfitting while support vector machine delivers encouraging results. Overall, our results provide material to construct small-cap and large-cap coverage indexes from specialized financial media.

Keywords: Textual analysis; Machine learning; Style investing (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-031-29050-3_8

Ordering information: This item can be ordered from
http://www.springer.com/9783031290503

DOI: 10.1007/978-3-031-29050-3_8

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().