Macroeconomic Forecasting with Large Language Models

TL;DR

This study compares the forecasting accuracy of Large Language Models with traditional macroeconomic methods using the FRED-MD database, highlighting their respective strengths and limitations in real-world applications.

Contribution

It provides a systematic evaluation of LLMs for macroeconomic forecasting, an area with limited prior comparative analysis.

Findings

LLMs perform comparably to traditional methods in some scenarios

Traditional methods still outperform LLMs in certain macroeconomic forecasts

Insights into when LLMs are most effective for macroeconomic data

Abstract

This paper presents a comparative analysis evaluating the accuracy of Large Language Models (LLMs) against traditional macro time series forecasting approaches. In recent times, LLMs have surged in popularity for forecasting due to their ability to capture intricate patterns in data and quickly adapt across very different domains. However, their effectiveness in forecasting macroeconomic time series data compared to conventional methods remains an area of interest. To address this, we conduct a rigorous evaluation of LLMs against traditional macro forecasting methods, using as common ground the FRED-MD database. Our findings provide valuable insights into the strengths and limitations of LLMs in forecasting macroeconomic time series, shedding light on their applicability in real-world scenarios