ChatGPT can forecast stock price movement with better accuracy than humans: Study

Artificial Intelligence (AI) is transforming various industries, and the finance sector is not left out. A recent study conducted by researchers at the University of Florida shows that ChatGPT, a large language model, can accurately forecast stock market returns using sentiment analysis of news headlines.

The study, titled "Return Predictability and Large Language Models," found that ChatGPT outperformed traditional sentiment analysis methods provided by leading vendors. The researchers leveraged ChatGPT's sentiment analysis capabilities to analyze news headlines and predict whether they were good, bad, or irrelevant news for firms' stock prices. They then computed a numerical score and documented a positive correlation between these "ChatGPT scores" and subsequent daily stock market returns.

The research has significant implications for the finance industry. According to the paper, this finding has the potential to shift the methods used for market prediction and investment decision-making.

The paper will demonstrate the value of ChatGPT and other LLMs in financial economics. It also aims to contribute to the understanding of such applications in this field and inspire further research on integrating artificial intelligence in financial markets.

Data Set for the Research

The researchers used two main sets of data for their study: daily stock returns from the Center for Research in Security Prices (CRSP) and news headlines. They looked at the relationship between the sentiment scores generated by ChatGPT and the corresponding stock market returns.

They collected news headlines for all companies listed on the NYSE, NASDAQ, and AMEX that had at least one news story covered by the data vendor. They used a relevance score to determine how closely the news pertains to a specific company and only included full articles and press releases with a relevance score of 100.

They also excluded headlines categorized as 'stock-gain' and 'stock-loss' and removed duplicate headlines for the same company on the same day and extremely similar headlines. The researchers claim that they made sure not to introduce any look-ahead bias in their analysis.

Also read: AI chatbots like ChatGPT will have human-like teaching capabilities in future: Bill Gates

Impact on Policies Around AI and Stock Markets 

The implications of the study go beyond the finance industry, as it could benefit regulators and policymakers in understanding the potential benefits and risks associated with the increasing adoption of LLMs in financial markets.

The paper claims that as these language models become more prevalent, their influence on market behavior, information dissemination, and price formation will become critical areas of concern. The findings of the study can help develop regulatory frameworks that govern the use of AI in finance.

Asset managers and institutional investors can also benefit from the study by providing empirical evidence on the efficacy of LLMs in predicting stock market returns. This insight can help these professionals make more informed decisions about incorporating LLMs into their investment strategies, potentially leading to improved performance and reduced reliance on traditional, more labor-intensive analysis methods.

Also read: ChatGPT spooks the internet with a 2-line horror story and we are trembling too

Future of AI-driven Finance

The paper suggests that as AI-driven finance evolves, more sophisticated models can be designed to improve the accuracy and efficiency of financial decision-making processes. Future research should focus on understanding the mechanisms through which LLMs derive their predictive power.