Authors:
(1) Pham Hoang Van, Department of Economics, Baylor University Waco, TX, USA (Van [email protected]);
(2) Scott Cunningham, Department of Economics, Baylor University Waco, TX, USA (Scott [email protected]).
Table of Links
Abstract and 1 Introduction
2 Direct vs Narrative Prediction
3 Prompting Methodology and Data Collection
4 Results
4.1 Establishing the Training Data Limit with Falsifications
4.2 Results of the 2022 Academy Awards Forecasts
5 Predicting Macroeconomic Variables
5.1 Predicting Inflation with an Economics Professor
5.2 Predicting Inflation with a Jerome Powell, Fed Chair
5.3 Predicting Inflation with Jerome Powell and Prompting with Russia’s Invasion of Ukraine
5.4 Predicting Unemployment with an Economics Professor
6 Conjecture on ChatGPT-4’s Predictive Abilities in Narrative Form
7 Conclusion and Acknowledgments
Appendix
A. Distribution of Predicted Academy Award Winners
B. Distribution of Predicted Macroeconomic Variables
References
B. Distribution of Predicted Macroeconomic Variables
This section contains figures that demonstrate the distribution of predicted macroeconomic variables, such as inflation and unemployment, using the four prompting styles. The results highlight the enhanced predictive power of GPT-4 when using the future narrative approach.
References
Agrawal, A., Gans, J., and Goldfarb, A. (2018). Prediction Machines: The Simple Economics of Artificial Intelligence. Harvard Business Review Press, Boston, MA, USA.
Brand, J., Israeli, A., and Ngwe, D. (2023). Using gpt for market research. Working Paper 23-062, Harvard Business School Marketing Unit.
Horton, J. J. (2023). Large language models as simulated economic agents: What can we learn from homo silicus? https://doi.org/10.48550/arXiv.2301.07543.
Hughes, A. (2023). ChatGPT: Everything you need to know about OpenAI’s GPT-4 tool. BBC Science Focus, September 25, 2023.
Kim, A. G., Muhn, M., and Nikolaev, V. (2023). From transcripts to insights: Uncovering corporate risks using generative AI. Working Paper 2023-132, Becker Friedman Institute.
Levy, S. (2024). In defense of AI hallucinations. Wired, January 5, 2024.
Lopez-Lira, A. and Tang, Y. (2023). Can chatgpt forecast stock price movements? return predictability and large language models. http://dx.doi.org/10.2139/ ssrn.4412788.
Mehdi, Y. (2023). Bing at Microsoft Build 2023: Continuing the Transformation of Search, May 23, 2023. https://blogs.bing.com/search/may_2023/ Bing-at-Microsoft-Build-2023. Accessed: April 07, 2024.
OpenAI (2024a). OpenAI–Documentation–Models. https://platform.openai. com/docs/models/gpt-4-and-gpt-4-turbo. Accessed: April 06, 2024.
OpenAI (2024b). Usage Policies. https://openai.com/policies/ usage-policies. Accessed: April 10, 2024.
Schaul, K., Chen, S. Y., and Tiku, N. (2023). Inside the secret list of websites that make AI like ChatGPT sound smart. Washington Post, April 19, 2023.
Silver, N. (2013). Oscar Predictions, Election-Style. https://fivethirtyeight. com/features/oscar-predictions-election-style/. Accessed: April 09, 2024.
aswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 6000–6010, Red Hook, NY, USA. Curran Associates Inc.
