voidly

AzerbaijanAZ

falling (-21.9pp)

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
76.5%
d14 · 2026-08-27
Floor day
27.7%
d26 · 2026-09-08
30-day delta
-21.9pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d14 76%
mean P(shutdown by day)90% conformal bandpeak day

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

day 150.5%
2026-08-14
  • block_rate_roll7_mean-0.027
  • block_rate_roll7_std-0.022
  • verified_signals_7d-0.012
day 757.1%
2026-08-20
  • block_rate_roll7_mean-0.027
  • block_rate_roll7_std-0.022
  • verified_signals_7d-0.012
day 1476.5%
2026-08-27
  • block_rate_roll7_mean-0.027
  • block_rate_roll7_std-0.022
  • verified_signals_7d-0.012
day 3028.6%
2026-09-12
  • block_rate_roll7_mean-0.027
  • block_rate_roll7_std-0.022
  • verified_signals_7d-0.012

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
d12026-08-1450.5%[7%, 94%]
d72026-08-2057.1%[0%, 100%]
d142026-08-2776.5%[8%, 100%]
d302026-09-1228.6%[0%, 100%]
Spotlight countries