Artificial Intelligence and Inflation Forecasts

RePEc Short ID: pfa225
ORCID iD: 0000-0002-3759-2172

Faria-e-Castro, Miguel; Leibovici, Fernando

doi:10.20955/r.2024.12

Journal Article

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.

Keywords: large language models (LLMs); artificial intelligence (AI); inflation forecasts; Survey of Professional Forecasters (SPF);

JEL Classification: C45; C53; E31; E37;

https://doi.org/10.20955/r.2024.12