How can we use ChatGPT better: A research of API-Enhanced ChatGPT in stock prediction
Open accessAbstract
In this study, we propose an API-enhanced ChatGPT structure that incorporates stock price and news data to improve stock price movement predictions. By integrating external data sources and prompt engineering techniques, our approach demonstrates a significant improvement in predictive performance compared to using only stock price data. The inclusion of news data alongside stock prices results in an approximately 10% increase in accuracy and F1 scores, as well as a 20% improvement in risk-adjusted returns, as measured by Sharpe ratios and information ratios. Our findings highlight the potential of leveraging conversational AI and large language models for stock market analysis, while also identifying areas for further research and optimization, such as addressing stock-specific challenges and developing cost-effective strategies for implementation. This study contributes to the limited body of literature on the application of large language models in finance and paves the way for future research in enhancing the capabilities of AI-driven investment decision-making tools
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In [18] and [60], F1 score and accuracy are used to measure model's prediction accuracy of news sentiment.
“In [18] and [60], the F1 score and accuracy are used to measure the model's prediction accuracy of news sentiment.”
From Large Language Model Agent in Financial Trading: A Survey (2026) · cites this paper as [60]
Cited by
Sorted by citations
Large Language Model Agent in Financial Trading: A Survey
Ding, H., Li, Y., Wang, J., Chen, H., Guo, D., & Zhang, Y. (2026) · Proceedings of the 2026 9th International Conference on Computers in Management and Business · doi:10.1145/3802463.3802475 · Cited by 10 · see citing works
- Authors
- Zheng, Q.
- Affiliations
- University of Chicago (US)
- Corresponding author
- Zheng, Qichang
- Venue
- University of Chicago
- Publisher
- University of Chicago
- Published
- 2024-06
- OpenAlex
- W6901865708
- Cited by
- 0
- References
- 0
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- Knowledge@UChicago (University of Chicago) (submittedVersion)
- University of Chicago
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Social Sciences › Business, Management and Accounting › Accounting › Financial Analysis and Corporate Governance
- Keywords
- ChatGPT, stock price prediction, API integration, news data, prompt engineering, stock market analysis, risk-adjusted returns, investment decision-making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
