Sentiment Trading with Large Language Models

Finance Research Letters, 62, 105227. doi: 10.1016/j.frl.2024.105227

14 Pages Posted: 25 Jan 2024 Last revised: 26 Mar 2024

See all articles by Kemal Kirtac

Kemal Kirtac

University College London

Guido Germano

University College London; London School of Economics and Political Science

Date Written: March 21, 2024

Abstract

We analyse the performance of the large language models (LLMs) OPT, BERT, and FINBERT, alongside the traditional Loughran-McDonald dictionary, in the sentiment analysis of 965,375 U.S. financial news articles from 2010 to 2023. Our findings reveal that the GPT-3-based OPT model significantly outperforms the others, predicting stock market returns with an accuracy of 74.4%. A long-short strategy based on OPT, accounting for 10 basis points (bps) in transaction costs, yields an exceptional Sharpe ratio of 3.05. From August 2021 to July 2023, this strategy produces an impressive 355% gain, outperforming both other strategies and traditional market portfolios. This underscores the transformative potential of LLMs in financial market prediction and portfolio management and the necessity of employing sophisticated language models to develop effective investment strategies based on news sentiment.

Keywords: Natural language processing (NLP), Large language model (LLM), Generative pretrained transformer (GPT), Machine learning in stock return prediction, Artificial intelligence investment strategies

JEL Classification: C53, G10, G11, G12, G14, G17

Suggested Citation

Kirtac, K. and Germano, G., Sentiment Trading with Large Language Models (March 21, 2024). Finance Research Letters, 62, 105227. doi: 10.1016/j.frl.2024.105227, Available at SSRN: https://ssrn.com/abstract=4706629 or http://dx.doi.org/10.2139/ssrn.4706629

K. Kirtac (Contact Author)

University College London ( email )

Department of Computer Science
66-72 Gower Street
London, WC2A 2AE
United Kingdom

G. Germano

University College London ( email )

Department of Computer Science
66-72 Gower Street
London, WC1E 6EA
United Kingdom
+44 20 3108 7105 (Phone)
+44 20 7387 1397 (Fax)

HOME PAGE: http://www.cs.ucl.ac.uk/staff/g.germano

London School of Economics and Political Science ( email )

Systemic Risk Centre
Houghton Street
London, WC2A 2AE
United Kingdom
+44 20 3108 7105 (Phone)
+44 20 7387 1397 (Fax)

HOME PAGE: http://www.systemicrisk.ac.uk/people/guido-germano

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
667
Abstract Views
3,291
Rank
81,919
PlumX Metrics