A daily measure of geopolitical risk constructed using large language models, covering 1960 to present.
The AI-GPR Index measures geopolitical risk by applying large language models (LLMs) to newspaper articles. Building on the conceptual framework of the original GPR Index (Caldara and Iacoviello, 2022), it replaces keyword matching with semantic understanding: instead of searching for specific word combinations, GPT-4o-mini reads each article and assigns a continuous risk score from 0.0 to 1.0 based on the article's geopolitical content.
The index is constructed at daily frequency using articles from the New York Times, Washington Post, and Chicago Tribune, spanning 1960 through 2025.
The main index. Aggregates LLM-assigned geopolitical risk scores across all newspaper articles on each date, normalized by total newspaper article count. Captures the overall level of geopolitical risk as perceived in the news.
A keyword-based GPR index constructed using the Caldara and Iacoviello (2022) proximity search methodology on the same three newspapers. Counts articles matching specific combinations of geopolitical and risk-related terms. Extended back to 1960.
A sub-index identifying articles that discuss oil or energy supply disruptions driven by geopolitical events. Constructed using a second LLM classification layer applied to high-GPR articles containing oil-related keywords.
Articles matching a broad keyword filter are scored by GPT-4o-mini on a 0–1 scale reflecting the intensity of geopolitical risk content. All indices are normalized to a mean of 100 over 1985–2019. See the paper for full details.
Use the range slider below the chart to zoom into specific periods. Hover over the chart for exact values. Double-click to reset zoom.
The data files contain the AI-GPR index, the keyword-based GPR index, and the GPR oil disruption sub-index. All indices are normalized to a mean of 100 over 1985–2019.
| File | Description | Columns | |
|---|---|---|---|
| ai_gpr_data_daily.csv | Daily index values, 1960–2025 | Date, GPR_AI, GPR_AER, GPR_OIL | Download |
| ai_gpr_data_monthly.csv | Monthly averages, 1960–2025 | Date, GPR_AI, GPR_AER, GPR_OIL | Download |
Last updated: February 2026 with data through December 2025.
When using the data, please cite the paper and note the date of download.
Iacoviello, Matteo and Jonathan Tong (2026). “The AI-GPR Index: Measuring Geopolitical Risk using Artificial Intelligence.” Working Paper.
When using the data, we suggest referring to both the website and the date of download; e.g., “Data downloaded from https://www.matteoiacoviello.com/ai_gpr.html on [Month DD, YYYY].”