Enhancing Stock Price Prediction using StockGPT: An Empirical Study on the Effectiveness of Macroeconomic Indicators
Abstract
This study explores the enhancement of stock price prediction using StockGPT, a transformer-based generative model, by integrating macroeconomic indicators and feature engineering techniques. Using data from U.S. tech stocks and the S&P 500 index, the proposed model demonstrated approximately a 1.16% improvement in RMSE over the baseline. Feature importance analysis using Permutation Importance revealed that the lagged USD Index and the moving average of WTI oil prices significantly contributed to prediction accuracy. The findings underscore the practical impact of incorporating structured external variables into generative models and offer insights into interpretable financial forecasting.
References
- Chauhan, A., Singh, R., and Sharma, P., “Enhancing stock market prediction using Informer Transformer and sentiment analysis,” Journal of Computational Finance and Economics, vol. 17, no. 1, pp. 45–63, 2025.
- Chen, L., Zhao, W., and Lin, M., “Improving economic indicator forecasts with Transformer-based models,” International Journal of Forecasting, vol. 41, no. 2, pp. 112–127, 2025.
- Jin, X., Hong, S., and Yu, K., “Time-series feature engineering for deep learning in financial forecasting,” Finance and AI Review, vol. 1, no. 1, pp. 22–45, 2023.
- Kang, J., and Bae, Y., “Feature-level fusion of financial and economic data for stock forecasting,” Expert Systems with Applications, vol. 213, p. 119124, 2023.
- Kim, H., and Kim, J., “Macroeconomic indicators and stock market prediction using Transformer-based models,” Journal of Financial Data Science, vol. 5, no. 2, pp. 55–72, 2023.
- Liu, Y., and Zhang, M., “Top-down vs bottom-up approaches in financial forecasting: A hybrid deep learning model,” Applied Soft Computing, vol. 116, p. 108313, 2022.
- Mai, J., “StockGPT: Generative Pre-trained Transformer for stock prediction,” Proceedings of the International Conference on AI in Finance, pp. 68–77, 2024.
- Nguyen, T., and Cho, S., “Deep learning in finance: From stock prices to macroeconomics,” IEEE Transactions on Neural Networks, vol. 33, no. 5, pp. 2434–2449, 2022.
- Papageorgiou, A., Liakopoulos, A., and Koulis, T., “Deep reinforcement learning for financial market prediction,” Machine Learning in Finance, vol. 9, no. 3, pp. 199–214, 2024.
- Wang, C., and Lee, D., “Explainable AI for financial time series using permutation importance,” AI in Finance Journal, vol. 3, no. 3, pp. 88–104, 2023.
- Wu, J., Wang, Z., and Lin, D., “BloombergGPT: A large language model tailored for finance,” arXiv preprint arXiv:2304.03285, 2023.
- Yang, Y., Chen, H., and Xu, Y., “FinGPT: Open-source financial LLM for financial data analysis,” arXiv preprint arXiv:2306.03085, 2023.
- Zhou, Z., and Tang, Q., “Economic sentiment vs. quantitative indicators: Which drives predictive performance?,” Quantitative Finance Letters, vol. 8, no. 1, pp. 14–29, 2024.
Keywords
Details
| Section | Articles |
| Issue | Vol. 2 No. 1 (2025): Volume 2 Issue 1 (November 2025) |
| Published | 2025-11-28 |
| Pages | 50-57 |
- Dongduk Women's University, B.S. in Computer Science, Class of 2001
- Seoul School of Integrated Sciences & Technologies (aSSIST), M.S. in AI and Big Data, Class of 2025
- Manager, PG Information Development Office, NICE Information & Telecommunication Co., Ltd. (since 2014)
- Research Interests: AI Interpretability, AI-Driven Financial Forecasting, FinTech Innovation, and Data Governance
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.