Large language models: a primer for economists

Byeungchun Kwon, Taejin Park, Fernando Perez-Cruz and Phurichai Rungcharoenkitkul

BIS Quarterly Review, 2024

Abstract: Large language models (LLMs) are powerful tools for analysing textual data, with substantial untapped potential in economic and central banking applications. Vast archives of text, including policy statements, financial reports and news, offer rich opportunities for analysis. This special feature provides an accessible introduction to LLMs aimed at economists and offers applied researchers a practical walkthrough of their use. We provide a step-by-step guide on the use of LLMs covering data organisation, signal extraction, quantitative analysis and output evaluation. As an illustration, we apply the framework to analyse perceived drivers of stock market dynamics based on over 60,000 news articles between 2021 and 2023. While macroeconomic and monetary policy news are important, market sentiment also exerts substantial influence.

JEL-codes: C55 C63 G10 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.bis.org/publ/qtrpdf/r_qt2412b.pdf (application/pdf)
http://www.bis.org/publ/qtrpdf/r_qt2412b.htm (text/html)

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:bis:bisqtr:2412b

Access Statistics for this article

BIS Quarterly Review is currently edited by Christian Upper

More articles in BIS Quarterly Review from Bank for International Settlements Contact information at EDIRC.
Bibliographic data for series maintained by Martin Fessler (webmaster@bis.org).