CubaCU
stable (-3.0pp)30-day day-by-day shutdown-risk trajectory. Each point is a per-horizon XGBoost prediction (h=1..30) with a 90% conformal band derived from absolute LOCO residuals. Peak risk highlighted.
Peak day
34.2%
d14 · 2026-08-27
Floor day
5.4%
d7 · 2026-08-20
30-day delta
-3.0pp
d30 vs d1 probability
30-day trajectory with 90% conformal band
model trajectory_v1mean P(shutdown by day)90% conformal bandpeak day
Drivers (SHAP top 3 from the 7-day model — same features feed all horizons)
day 111.0%
2026-08-14
- block_rate_roll7_std-0.026
- week_of_year-0.023
- gdelt_protests_7d-0.013
day 75.4%
2026-08-20
- block_rate_roll7_std-0.026
- week_of_year-0.023
- gdelt_protests_7d-0.013
day 1434.2%
2026-08-27
- block_rate_roll7_std-0.026
- week_of_year-0.023
- gdelt_protests_7d-0.013
day 308.0%
2026-09-12
- block_rate_roll7_std-0.026
- week_of_year-0.023
- gdelt_protests_7d-0.013
Honest caveats
- Per-horizon XGBoost stacked into a trajectory — not a true joint distribution.
- Conformal bands are absolute-residual q90 from LOCO predictions on 18 eval countries.
- Long horizons (h>=14d) have wider effective uncertainty than the conformal q90 suggests; the same lag features feed all horizons.
- Bands floor at [0,1]; probabilities below 0.05 are at the model's noise floor.
- SHAP attribution above is from the 7-day point model. The trajectory uses 30 separate per-horizon XGBoost models that share the same feature set; we have not yet computed per-horizon SHAP.
Sample horizons
| Day | Date | P(shutdown) | 90% interval |
|---|---|---|---|
| d1 | 2026-08-14 | 11.0% | [0%, 55%] |
| d7 | 2026-08-20 | 5.4% | [0%, 70%] |
| d14 | 2026-08-27 | 34.2% | [0%, 100%] |
| d30 | 2026-09-12 | 8.0% | [0%, 86%] |
Spotlight countries