The AI-GPR Index: Measuring Geopolitical Risk using Artificial Intelligence

Authors

Matteo Iacoviello, Jonathan Tong

Posted to EERN: March 24, 2026

FEDERAL RESERVE RESEARCH: Board of Governors

We introduce an improved measure of geopolitical risk that builds on Caldara and Iacoviello (2022) and uses artificial intelligence to evaluate newspaper content. Our approach replaces keyword matching with semantic understanding: instead of searching for specific word combinations, we use one of the language models underlying ChatGPT (GPT-4o-mini) to read newspaper articles and assess their geopolitical risk intensity. The daily AI-GPR index scores about 5 million articles from the New York Times, Washington Post, and Chicago Tribune from 1960 through 2025. The approach reduces false positives from articles mentioning war or terrorism in non-geopolitical contexts while capturing relevant articles that lack exact or common dictionary terms. The AI-GPR index also assigns gradations of risk intensity rather than simple yes-or-no classifications, providing more nuanced measurement even at high frequencies. We demonstrate the potential of our approach with three applications: the AI-GPR index improves the estimated negative effect of geopolitical risk on stock returns; combined with a second classification layer, it produces a historical time series of geopolitical risk-driven oil supply disruptions by region; and, using a third classification layer, it maps directed networks of geopolitical actors—initiators, respondents, and spillover countries—across major historical episodes.

Read the paper