Artificial Intelligence and Inflation Forecasts
Abstract
We explore the ability of large language models (LLMs) to produce in-sample conditional inflation forecasts during the 2019–23 period. We use a leading LLM (Google AI’s PaLM) to produce distributions of conditional forecasts at different horizons and compare these forecasts to those of a leading source, the Survey of Professional Forecasters (SPF). We find that LLM forecasts generate lower mean-squared errors overall in most years and at almost all horizons. LLM forecasts exhibit slower reversion to the 2 percent inflation anchor.
Introduction
Forecasting inflation lies at the heart of economic decisionmaking, shaping the financial planning of households, guiding strategic investments by firms, and driving monetary policy. However, it is a difficult task as equilibrium inflation is the outcome of the aggregation of individual actions that depend on, among other factors, the expectations of inflation itself.
In this article, we investigate the potential of state-of-the-art large language models (LLMs) in generating accurate inflation forecasts. To do so, we use Google’s PaLM LLM to construct retrospective inflation forecasts, which we contrast with a leading source of inflation forecasts, the Survey of Professional Forecasters (SPF), and with actual inflation data. We find that the LLM’s forecasts have lower mean-squared errors (MSEs) overall inmost years, and at almost all horizons, than the SPF.
These findings suggest that LLM models may provide an inexpensive and accurate complementary approach to generating inflation forecasts, with potential applicability to other macroeconomic variables. Traditional methods for inflation forecasting include expert surveys, individual surveys, measures of market-based expectations, and model-based expectations. Each has its strengths but also comes with limitations.
Citation
Miguel Faria-e-Castro and Fernando Leibovici, "Artificial Intelligence and Inflation Forecasts," Federal Reserve Bank of St. Louis Review, Fourth Quarter 2024, Vol. 106, No. 12, pp. 1-14.
https://doi.org/10.20955/r.2024.12
Editors in Chief
Michael Owyang and Juan Sanchez
This journal of scholarly research delves into monetary policy, macroeconomics, and more. Views expressed are not necessarily those of the St. Louis Fed or Federal Reserve System. View the full archive (pre-2018).
Email Us