Headline-Driven Classification and Local Interpretation for Market Outperformance and Low-Risk Stock Prediction

Daniil Karzanov ()
Additional contact information
Daniil Karzanov: École polytechnique fédérale de Lausanne (EPFL)

Computational Economics, 2024, vol. 64, issue 2, No 6, 769-788

Abstract: Abstract Financial news is one of the most influential sources for making long-term investment decisions. The goal of this paper is to learn whether it is possible, based on texts from news headlines, to select stocks with low forecasted volatility which outrun the market represented by the Standard and Poor’s 500 Index. We solve several binary classification problems using a range of machine learning and deep learning principles. The best classifiers are interpreted with a model-agnostic technique, LIME, to extract key words having the greatest impact on the probabilities of market outrun and low volatility.

Keywords: Machine learning; NLP; Interpretability; Financial sentiment analysis; Stock market (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-023-10449-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:kap:compec:v:64:y:2024:i:2:d:10.1007_s10614-023-10449-5

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-023-10449-5

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().