voidly

BelarusBY

climbing (+24.3pp)

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
68.9%
d10 · 2026-07-16
Floor day
3.1%
d2 · 2026-07-08
30-day delta
+24.3pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d10 69%
mean P(shutdown by day)90% conformal bandpeak day

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

day 18.8%
2026-07-07
  • week_of_year-0.013
  • gdelt_protests_7d-0.011
  • month-0.009
day 79.1%
2026-07-13
  • week_of_year-0.013
  • gdelt_protests_7d-0.011
  • month-0.009
day 1444.0%
2026-07-20
  • week_of_year-0.013
  • gdelt_protests_7d-0.011
  • month-0.009
day 3033.1%
2026-08-05
  • week_of_year-0.013
  • gdelt_protests_7d-0.011
  • month-0.009

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
d12026-07-078.8%[0%, 53%]
d72026-07-139.1%[0%, 74%]
d142026-07-2044.0%[0%, 100%]
d302026-08-0533.1%[0%, 100%]
Spotlight countries