voidly
← Atlas

TajikistanTJ

falling (-5.1pp)

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
27.3%
d15 · 2026-09-05
Floor day
8.9%
d8 · 2026-08-29
30-day delta
-5.1pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%d1d7d14d21d30peak d15 27%
mean P(shutdown by day)90% conformal bandpeak day

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

day 117.4%
2026-08-22
  • week_of_year-0.025
  • block_rate_roll30_mean-0.023
  • verified_signals_7d-0.012
day 79.9%
2026-08-28
  • week_of_year-0.025
  • block_rate_roll30_mean-0.023
  • verified_signals_7d-0.012
day 1424.9%
2026-09-04
  • week_of_year-0.025
  • block_rate_roll30_mean-0.023
  • verified_signals_7d-0.012
day 3012.2%
2026-09-20
  • week_of_year-0.025
  • block_rate_roll30_mean-0.023
  • 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
d12026-08-2217.4%[0%, 61%]
d72026-08-289.9%[0%, 75%]
d142026-09-0424.9%[0%, 94%]
d302026-09-2012.2%[0%, 90%]
Spotlight countries