Sentiment trading with large language models
Study analyzes large language models' performance in predicting stock returns using sentiment from financial news articles.
What it examines
This paper explores the use of large language models (LLMs) like OPT, BERT, and FinBERT for sentiment analysis in financial news to predict stock returns. It aims to enhance financial text mining by leveraging advanced LLMs to develop more accurate investment strategies based on news sentiment.
What it concludes
The research demonstrates the effectiveness of LLMs in predicting stock returns and developing investment strategies. Potential applications include enhancing market prediction and investment decision-making methodologies, with implications for asset managers, institutional investors, and financial regulators.
Evidence objects
The research demonstrates the effectiveness of LLMs in predicting stock returns and developing investment strategies. Potential applications include enhancing market prediction and investment decision-making methodologies, with implications for asset managers, institutional investors, and financial regulators.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
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.
Source row: 1760 · abstract type: unknown