可预测性
金融经济学
股票价格
计量经济学
库存(枪支)
经济
地理
数学
地质学
统计
系列(地层学)
考古
古生物学
作者
Alejandro Lopez-Lira,Yuehua Tang
出处
期刊:Social Science Research Network
[Social Science Electronic Publishing]
日期:2023-01-01
被引量:90
摘要
We examine the potential of ChatGPT, and other large language models, in predicting stock market returns using sentiment analysis of news headlines. We use ChatGPT to indicate whether a given headline is good, bad, or irrelevant news for firms' stock prices. We then compute a numerical score and document a positive correlation between these ChatGPT scores and subsequent daily stock market returns. Further, ChatGPT outperforms traditional sentiment analysis methods. We find that more basic models such as GPT-1, GPT-2, and BERT cannot accurately forecast returns, indicating return predictability is an emerging capacity of complex models. Our results suggest that incorporating advanced language models into the investment decision-making process can yield more accurate predictions and enhance the performance of quantitative trading strategies.
科研通智能强力驱动
Strongly Powered by AbleSci AI