Sentiment trading with large language models

Kirtac, Kemal and Germano, Guido (2024) Sentiment trading with large language models. Finance Research Letters, 62 (Part B). ISSN 1544-6123

Text (1-s2.0-S1544612324002575-main) - Published Version Available under License Creative Commons Attribution. Download (1MB)

• Scopus publication
• Author

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 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.

Item Type:	Article
Official URL:	https://www.sciencedirect.com/journal/finance-rese...
Additional Information:	© 2024 The Author
Divisions:	Management Systemic Risk Centre
Subjects:	Q Science > Q Science (General) H Social Sciences > HG Finance
JEL classification:	C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C53 - Forecasting and Other Model Applications G - Financial Economics > G1 - General Financial Markets > G10 - General G - Financial Economics > G1 - General Financial Markets > G11 - Portfolio Choice; Investment Decisions G - Financial Economics > G1 - General Financial Markets > G12 - Asset Pricing; Trading volume; Bond Interest Rates G - Financial Economics > G1 - General Financial Markets > G14 - Information and Market Efficiency; Event Studies
Date Deposited:	09 Apr 2024 14:21
Last Modified:	22 Nov 2024 06:18
URI:	http://eprints.lse.ac.uk/id/eprint/122592

Actions (login required)

View Item