CubaCU
stable (+2.2pp)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
53.8%
d7 · 2026-05-29
Floor day
15.6%
d1 · 2026-05-23
30-day delta
+2.2pp
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 115.6%
2026-05-23
- gdelt_unrest_30d-0.030
- recent_shutdown+0.015
- week_of_year+0.013
day 753.8%
2026-05-29
- gdelt_unrest_30d-0.030
- recent_shutdown+0.015
- week_of_year+0.013
day 1441.9%
2026-06-05
- gdelt_unrest_30d-0.030
- recent_shutdown+0.015
- week_of_year+0.013
day 3017.8%
2026-06-21
- gdelt_unrest_30d-0.030
- recent_shutdown+0.015
- week_of_year+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 | 2026-05-23 | 15.6% | [0%, 60%] |
| d7 | 2026-05-29 | 53.8% | [0%, 100%] |
| d14 | 2026-06-05 | 41.9% | [0%, 100%] |
| d30 | 2026-06-21 | 17.8% | [0%, 96%] |
Spotlight countries