Learning the Macroeconomic Language

2025/12/24 by Siddhartha Chib, Fei Tan, Chib, Siddhartha +1
Decision Sciences · Social Sciences · #Stock Market Forecasting Methods #Forecasting Techniques and Applications #Computational and Text Analysis Methods

paper · doi:10.48550/arxiv.2512.21031

Abstract

We show how state-of-the-art large language models (LLMs), seemingly inapplicable to the small samples typical of macroeconomics, can be trained effectively for macroeconomic forecasting. We estimate a dynamic stochastic general equilibrium (DSGE) model on an initial segment of the data to obtain a posterior distribution over structural parameters. We sample from this posterior to generate millions of theory-consistent synthetic panels that, when mixed with actual macroeconomic data, form the training corpus for a time-series transformer with attention. The trained model is then used to forecast out-of-sample through 2025. The results show that this hybrid forecaster, which combines the theoretical coherence of DSGE models with the representational power of modern LLMs, learns key features of the macroeconomic language.

Citations

• Kronos: A Foundation Model for the Language of Financial Markets
• CARLA: An Open Urban Driving Simulator
• Attention Is All You Need
• Domain Randomization for Transferring Deep Neural Networks from\n Simulation to the Real World
• Shocks and Frictions in US Business Cycles: A Bayesian DSGE Approach

Related

• Macroeconomic Forecasting with Large Language Models
• Macroeconomic Forecasting and Machine Learning
• How is Machine Learning Useful for Macroeconomic Forecasting?
• Improving Macroeconomic Model Validity and Forecasting Performance with\n Pooled Country Data using Structural, Reduced Form, and Neural Network Model
• Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas