Presenter: Daniela Puzzello
Affiliation: Indiana University, Department of Economics.
Paper: Simulating the Survey of Professional Forecasters.
Date: February 25, 2025.
Time: 13:00 GMT (15:00 Israel Time)
Abstract: We simulate economic forecasts of professional forecasters using large language models (LLMs). We construct synthetic forecaster personas using a unique hand-gathered dataset of participant characteristics from the Survey of Professional Forecasters. These personas are then provided with real-time macroeconomic data to generate simulated responses to the SPF survey. Our results show that LLM-generated predictions are similar to human forecasts, but often achieve superior accuracy, particularly at medium- and long-term horizons. We argue that this advantage arises from LLMs’ ability to extract latent information encoded in past human forecasts while avoiding systematic biases and noise. Our framework offers a cost-effective, high-frequency alternative that complements traditional survey methods by leveraging both human expertise and AI precision.
Coauthors: Anne Lundgaard Hansen (Federal Reserve Bank of Richmond), John J. Horton (MIT Sloan School of Management), Sophia Kazinnik (Stanford University), and Ali Zarifhonarvar (Indiana University).