Afghanistan AF
climbing (+8.7pp)Follow the model’s 30-day path. Read the probability and uncertainty together.
30-day model trajectory
model trajectory_v1mean P(shutdown by day)Uncertainty interval withheld: 90% coverage has not been validated.peak day
Peak day
30.7%
d20 · 2026-12-09
Floor day
5.9%
d1 · 2026-11-20
30-day delta
+8.7pp
d30 vs d1 probability
Drivers (SHAP top 3 from the 7-day model — same features feed all horizons)
day 15.9%
2026-11-20
- week_of_year-0.097
- block_rate_roll30_mean-0.064
- critical_incident_7d+0.041
day 77.8%
2026-11-26
- week_of_year-0.097
- block_rate_roll30_mean-0.064
- critical_incident_7d+0.041
day 1425.9%
2026-12-03
- week_of_year-0.097
- block_rate_roll30_mean-0.064
- critical_incident_7d+0.041
day 3014.6%
2026-12-19
- week_of_year-0.097
- block_rate_roll30_mean-0.064
- critical_incident_7d+0.041
Honest caveats
- Per-horizon XGBoost stacked into a trajectory — not a true joint distribution.
- The stored LOCO absolute-residual widths are not validated 90% intervals for these forecast probabilities; intervals are withheld.
- Long horizons (h>=14d) have additional uncertainty because the same lag features feed all horizons.
- 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) | Interval status |
|---|---|---|---|
| d1 | 2026-11-20 | 5.9% | Unvalidated |
| d7 | 2026-11-26 | 7.8% | Unvalidated |
| d14 | 2026-12-03 | 25.9% | Unvalidated |
| d30 | 2026-12-19 | 14.6% | Unvalidated |
Spotlight countries
About this view
30-day day-by-day shutdown-risk trajectory. Each point is a per-horizon XGBoost model score (h=1..30). The stored LOCO residual widths are not validated probability intervals, so no uncertainty band is shown. Peak score highlighted.