Human Against Machine: Are Professional Economists or AI Better at Forecasting Inflation?

As interest grows around the potential of artificial intelligence (AI) to forecast economic indicators, the US Federal Reserve has demonstrated some success in using it to forecast inflation.

Similar results have been obtained by broadening the Fed’s research to include other large language models (LLMs), countries and time horizons. LLMs have generally been at least as good as professional forecasters at projecting inflation since 2018, with 2023 being the only year that US and Canadian forecasters outperformed AI platforms in this area.

But AI isn’t without its limitations. In examining historical forecasting performance, it’s very difficult to prevent LLMs from “cheating” by taking into account information that wasn’t available when professional forecasters issued their projections. Further, some of the AI platforms’ technical characteristics can cause them to just naively repeat prior forecasts.

All told, AI should be considered a useful tool in the economic forecaster’s toolbox, especially since it incorporates different information than traditional tools. However, until an analysis is undertaken which properly controls for all of AI’s current limitations, it isn’t yet time to replace the human with the machine.