voidly

Azerbaijan AZ

stable (-2.1pp)

Follow the model’s 30-day path. Read the probability and uncertainty together.

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d18 81%
mean P(shutdown by day)90% conformal bandpeak day
Peak day
81.4%
d18 · 2026-10-02
Floor day
23.5%
d29 · 2026-10-13
30-day delta
-2.1pp
d30 vs d1 probability

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

day 137.3%
2026-09-15
  • block_rate_roll7_mean-0.106
  • week_of_year+0.050
  • block_rate_lag1-0.046
day 750.7%
2026-09-21
  • block_rate_roll7_mean-0.106
  • week_of_year+0.050
  • block_rate_lag1-0.046
day 1465.1%
2026-09-28
  • block_rate_roll7_mean-0.106
  • week_of_year+0.050
  • block_rate_lag1-0.046
day 3035.1%
2026-10-14
  • block_rate_roll7_mean-0.106
  • week_of_year+0.050
  • block_rate_lag1-0.046

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
d12026-09-1537.3%[0%, 81%]
d72026-09-2150.7%[0%, 100%]
d142026-09-2865.1%[0%, 100%]
d302026-10-1435.1%[0%, 100%]
Spotlight countries
About this view

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.