voidly

BelarusBY

climbing (+8.7pp)

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
50.6%
d19 · 2026-09-08
Floor day
0.9%
d3 · 2026-08-23
30-day delta
+8.7pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d19 51%
mean P(shutdown by day)90% conformal bandpeak day

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

day 16.2%
2026-08-21
  • week_of_year-0.078
  • month-0.025
  • risk_tier-0.022
day 726.3%
2026-08-27
  • week_of_year-0.078
  • month-0.025
  • risk_tier-0.022
day 1424.0%
2026-09-03
  • week_of_year-0.078
  • month-0.025
  • risk_tier-0.022
day 3014.9%
2026-09-19
  • week_of_year-0.078
  • month-0.025
  • risk_tier-0.022

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
d12026-08-216.2%[0%, 50%]
d72026-08-2726.3%[0%, 91%]
d142026-09-0324.0%[0%, 93%]
d302026-09-1914.9%[0%, 93%]
Spotlight countries