Voidly

Tajikistan TJ

stable (+1.1pp)

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

30-day model trajectory

model trajectory_v1
0%25%d1d7d14d21d30peak d30 22%
mean P(shutdown by day)Uncertainty interval withheld: 90% coverage has not been validated.peak day
Peak day
21.6%
d30 · 2026-12-19
Floor day
9.2%
d8 · 2026-11-27
30-day delta
+1.1pp
d30 vs d1 probability

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

day 120.5%
2026-11-20
  • week_of_year-0.080
  • block_rate_roll30_mean-0.055
  • gdelt_unrest_30d-0.040
day 710.8%
2026-11-26
  • week_of_year-0.080
  • block_rate_roll30_mean-0.055
  • gdelt_unrest_30d-0.040
day 1417.0%
2026-12-03
  • week_of_year-0.080
  • block_rate_roll30_mean-0.055
  • gdelt_unrest_30d-0.040
day 3021.6%
2026-12-19
  • week_of_year-0.080
  • block_rate_roll30_mean-0.055
  • gdelt_unrest_30d-0.040

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

DayDateP(shutdown)Interval status
d12026-11-2020.5%Unvalidated
d72026-11-2610.8%Unvalidated
d142026-12-0317.0%Unvalidated
d302026-12-1921.6%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.