voidly

EthiopiaET

climbing (+23.1pp)

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
29.9%
d28 · 2026-08-03
Floor day
2.7%
d2 · 2026-07-08
30-day delta
+23.1pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d28 30%
mean P(shutdown by day)90% conformal bandpeak day

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

day 15.4%
2026-07-07
  • incident_count_7d-0.005
  • month-0.005
  • risk_tier-0.005
day 76.7%
2026-07-13
  • incident_count_7d-0.005
  • month-0.005
  • risk_tier-0.005
day 1427.6%
2026-07-20
  • incident_count_7d-0.005
  • month-0.005
  • risk_tier-0.005
day 3028.6%
2026-08-05
  • incident_count_7d-0.005
  • month-0.005
  • risk_tier-0.005

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
d12026-07-075.4%[0%, 49%]
d72026-07-136.7%[0%, 71%]
d142026-07-2027.6%[0%, 96%]
d302026-08-0528.6%[0%, 100%]
Spotlight countries