Voidly

Iran IR

climbing (+7.1pp)

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

30-day model trajectory

model trajectory_v1
0%25%d1d7d14d21d30peak d19 36%
mean P(shutdown by day)Uncertainty interval withheld: 90% coverage has not been validated.peak day
Peak day
36.3%
d19 · 2026-10-31
Floor day
2.2%
d7 · 2026-10-19
30-day delta
+7.1pp
d30 vs d1 probability

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

day 13.1%
2026-10-13
  • block_rate_roll7_std-0.163
  • risk_tier-0.100
  • incident_count_7d-0.085
day 72.2%
2026-10-19
  • block_rate_roll7_std-0.163
  • risk_tier-0.100
  • incident_count_7d-0.085
day 1421.6%
2026-10-26
  • block_rate_roll7_std-0.163
  • risk_tier-0.100
  • incident_count_7d-0.085
day 3010.2%
2026-11-11
  • block_rate_roll7_std-0.163
  • risk_tier-0.100
  • incident_count_7d-0.085

Honest caveats

  • Per-horizon XGBoost stacked into a trajectory — not a true joint distribution.
  • The stored LOCO absolute-residual widths are not validated 90% intervals for these forecast probabilities; intervals are withheld.
  • Long horizons (h>=14d) have additional uncertainty because the same lag features feed all horizons.
  • 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)Interval status
d12026-10-133.1%Unvalidated
d72026-10-192.2%Unvalidated
d142026-10-2621.6%Unvalidated
d302026-11-1110.2%Unvalidated
Spotlight countries
About this view

30-day day-by-day shutdown-risk trajectory. Each point is a per-horizon XGBoost model score (h=1..30). The stored LOCO residual widths are not validated probability intervals, so no uncertainty band is shown. Peak score highlighted.