Track and predict high-stakes political outcomes at scale
Build models that forecast policy decisions, election outcomes, and geopolitical events. Historical records of political statements and outcomes provide rich temporal structure for future-as-label training.
The kinds of questions a model trained on your data can answer.
Benchmark comparisons against frontier models
Trump-Forecaster achieves lower Expected Calibration Error than GPT-5 in both context-aware (ECE 0.079 vs. 0.091) and context-free (ECE 0.164 vs. 0.191) settings — 13–14% better calibration, with the largest gains when no additional context is available.
Primary write-ups and artifacts for this solution.
Leverage your own raw data or use public sources. No labeling required.