Saudi ArabiaSA
climbing (+9.8pp)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
69.6%
d14 · 2026-09-04
Floor day
0.9%
d1 · 2026-08-22
30-day delta
+9.8pp
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 10.9%
2026-08-22
- month-0.056
- week_of_year-0.040
- block_rate_roll7_mean-0.020
day 732.9%
2026-08-28
- month-0.056
- week_of_year-0.040
- block_rate_roll7_mean-0.020
day 1469.6%
2026-09-04
- month-0.056
- week_of_year-0.040
- block_rate_roll7_mean-0.020
day 3010.8%
2026-09-20
- month-0.056
- week_of_year-0.040
- block_rate_roll7_mean-0.020
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 | 2026-08-22 | 0.9% | [0%, 45%] |
| d7 | 2026-08-28 | 32.9% | [0%, 98%] |
| d14 | 2026-09-04 | 69.6% | [1%, 100%] |
| d30 | 2026-09-20 | 10.8% | [0%, 89%] |
Spotlight countries