From Financial Reports to Macroeconomic Forecasts: An LLM-Based Approach
Abstract: Does the granular, qualitative information in corporate financial reports improve our understanding of aggregate economic activity? I use a Large Language Model to perform structured information extraction from over 20,000 SEC 10-K and 10-Q filings (2001–2025), quantifying firm-level operating conditions, labor shortages, and investment plans. Aggregated into size-weighted quarterly indices, these “textual factors” significantly improve out-of-sample GDP growth forecasts relative to standard benchmarks.