voidly

TajikistanTJ

climbing (+15.8pp)

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
34.5%
d7 · 2026-06-26
Floor day
11.7%
d18 · 2026-07-07
30-day delta
+15.8pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d7 35%
mean P(shutdown by day)90% conformal bandpeak day

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

day 114.9%
2026-06-20
  • week_of_year-0.022
  • recent_shutdown+0.010
  • risk_tier-0.008
day 734.5%
2026-06-26
  • week_of_year-0.022
  • recent_shutdown+0.010
  • risk_tier-0.008
day 1424.1%
2026-07-03
  • week_of_year-0.022
  • recent_shutdown+0.010
  • risk_tier-0.008
day 3030.8%
2026-07-19
  • week_of_year-0.022
  • recent_shutdown+0.010
  • risk_tier-0.008

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
d12026-06-2014.9%[0%, 59%]
d72026-06-2634.5%[0%, 99%]
d142026-07-0324.1%[0%, 93%]
d302026-07-1930.8%[0%, 100%]
Spotlight countries