voidly

UzbekistanUZ

falling (-19.7pp)

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
77.7%
d6 · 2026-08-26
Floor day
19.1%
d29 · 2026-09-18
30-day delta
-19.7pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d6 78%
mean P(shutdown by day)90% conformal bandpeak day

Drivers (SHAP top 3 from the 7-day model — same features feed all horizons)

day 140.3%
2026-08-21
  • month-0.079
  • week_of_year-0.040
  • gdelt_unrest_30d+0.029
day 741.0%
2026-08-27
  • month-0.079
  • week_of_year-0.040
  • gdelt_unrest_30d+0.029
day 1469.8%
2026-09-03
  • month-0.079
  • week_of_year-0.040
  • gdelt_unrest_30d+0.029
day 3020.6%
2026-09-19
  • month-0.079
  • week_of_year-0.040
  • gdelt_unrest_30d+0.029

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

DayDateP(shutdown)90% interval
d12026-08-2140.3%[0%, 84%]
d72026-08-2741.0%[0%, 100%]
d142026-09-0369.8%[1%, 100%]
d302026-09-1920.6%[0%, 99%]
Spotlight countries