Voidly

Ethiopia ET

climbing (+13.1pp)

Follow the model’s 30-day path. Read the probability and uncertainty together.

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d6 79%
mean P(shutdown by day)90% conformal bandpeak day
Peak day
78.7%
d6 · 2026-10-11
Floor day
9.1%
d1 · 2026-10-06
30-day delta
+13.1pp
d30 vs d1 probability

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

day 19.1%
2026-10-06
  • week_of_year-0.047
  • block_rate_roll7_mean-0.042
  • block_rate_lag3-0.032
day 730.7%
2026-10-12
  • week_of_year-0.047
  • block_rate_roll7_mean-0.042
  • block_rate_lag3-0.032
day 1425.4%
2026-10-19
  • week_of_year-0.047
  • block_rate_roll7_mean-0.042
  • block_rate_lag3-0.032
day 3022.2%
2026-11-04
  • week_of_year-0.047
  • block_rate_roll7_mean-0.042
  • block_rate_lag3-0.032

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
d12026-10-069.1%[0%, 53%]
d72026-10-1230.7%[0%, 95%]
d142026-10-1925.4%[0%, 94%]
d302026-11-0422.2%[0%, 100%]
Spotlight countries
About this view

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.