voidly

KazakhstanKZ

climbing (+30.8pp)

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
65.2%
d8 · 2026-05-30
Floor day
4.5%
d1 · 2026-05-23
30-day delta
+30.8pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d8 65%
mean P(shutdown by day)90% conformal bandpeak day

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

day 14.5%
2026-05-23
  • gdelt_unrest_30d+0.133
  • block_rate_roll30_mean-0.117
  • block_rate_lag14-0.083
day 755.8%
2026-05-29
  • gdelt_unrest_30d+0.133
  • block_rate_roll30_mean-0.117
  • block_rate_lag14-0.083
day 1437.5%
2026-06-05
  • gdelt_unrest_30d+0.133
  • block_rate_roll30_mean-0.117
  • block_rate_lag14-0.083
day 3035.3%
2026-06-21
  • gdelt_unrest_30d+0.133
  • block_rate_roll30_mean-0.117
  • block_rate_lag14-0.083

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
d12026-05-234.5%[0%, 48%]
d72026-05-2955.8%[0%, 100%]
d142026-06-0537.5%[0%, 100%]
d302026-06-2135.3%[0%, 100%]
Spotlight countries