paint-brush
ChatGPT's Macroeconomic Predictionsby@precedent
New Story

ChatGPT's Macroeconomic Predictions

by Precedent Publishing HouseMarch 19th, 2025
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

GPT-4’s predictions for inflation and unemployment improve with future narrative prompts. This section presents data showing how storytelling enhances AI’s ability to forecast macroeconomic trends.

People Mentioned

Mention Thumbnail

Company Mentioned

Mention Thumbnail
featured image - ChatGPT's Macroeconomic Predictions
Precedent Publishing House HackerNoon profile picture
0-item

Authors:

(1) Pham Hoang Van, Department of Economics, Baylor University Waco, TX, USA (Van Pham@baylor.edu);

(2) Scott Cunningham, Department of Economics, Baylor University Waco, TX, USA (Scott Cunningham@baylor.edu).

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.


Figure 11: Inflation Predictions with Direct Prompting (GPT3.5).


Figure 12: Inflation Predictions with Direct Prompting (GPT4).


Figure 13: Inflation Predictions by an ”Economist”(GPT3.5).


Figure 14: Inflation Predictions by an ”Economist”(GPT4).


Figure 15: Inflation Predictions by Fed Chair (GPT3.5).


Figure 16: Inflation Predictions by Fed Chair (GPT4).


Figure 17: Inflation Predictions by Fed Chair with Russian Invasion Information (GPT3.5).


Figure 18: Inflation Predictions by Fed Chair with Russian Invasion Information (GPT4).


Figure 19: Unemployment Predictions with Direct Prompting (GPT4).


Figure 20: Unemployment Predictions with Direct Prompting (GPT4).


Figure 21: Unemployment Predictions by an ”Economist”(GPT3.5).


Figure 22: Unemployment Predictions by an ”Economist”(GPT4).


Figure 23: Unemployment Predictions by Fed Chair (GPT3.5).


Figure 24: Unemployment Predictions by Fed Chair (GPT4).


Figure 25: Unemployment Predictions by Fed Chair with Russian Invasion Information (GPT3.5).


Figure 26: Unemployment Predictions by Fed Chair with Russian Invasion Information (GPT4).


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.


This paper is available on arxiv under CC BY 4.0 DEED license.