eprintid: 10190583 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/19/05/83 datestamp: 2024-04-10 16:30:31 lastmod: 2024-04-10 16:30:31 status_changed: 2024-04-10 16:30:31 type: article metadata_visibility: show sword_depositor: 699 creators_name: Kirtac, Kemal creators_name: Germano, Guido title: Sentiment trading with large language models ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Natural language processing (NLP), Large language models, Generative pre-trained transformer (GPT), Machine learning in stock return prediction, Artificial intelligence investment strategies note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. 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. date: 2024-04 date_type: published publisher: Elsevier BV official_url: http://dx.doi.org/10.1016/j.frl.2024.105227 full_text_type: other language: eng verified: verified_manual elements_id: 2266344 doi: 10.1016/j.frl.2024.105227 lyricists_name: Germano, Guido lyricists_id: GGERM33 actors_name: Kalinowski, Damian actors_id: DKALI47 actors_role: owner full_text_status: restricted publication: Finance Research Letters volume: 62 article_number: 105227 citation: Kirtac, Kemal; Germano, Guido; (2024) Sentiment trading with large language models. Finance Research Letters , 62 , Article 105227. 10.1016/j.frl.2024.105227 <https://doi.org/10.1016/j.frl.2024.105227>. document_url: https://discovery.ucl.ac.uk/id/eprint/10190583/1/Germano_Sentiment%20trading%20with%20large%20language%20models_AAM.pdf