voidly

IranIR

climbing (+5.6pp)

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
39.8%
d6 · 2026-05-28
Floor day
2.3%
d1 · 2026-05-23
30-day delta
+5.6pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d6 40%
mean P(shutdown by day)90% conformal bandpeak day

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

day 12.3%
2026-05-23
  • block_rate_roll7_mean-0.030
  • incident_count_7d+0.010
  • risk_tier-0.008
day 717.3%
2026-05-29
  • block_rate_roll7_mean-0.030
  • incident_count_7d+0.010
  • risk_tier-0.008
day 1424.5%
2026-06-05
  • block_rate_roll7_mean-0.030
  • incident_count_7d+0.010
  • risk_tier-0.008
day 308.0%
2026-06-21
  • block_rate_roll7_mean-0.030
  • incident_count_7d+0.010
  • risk_tier-0.008

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
d12026-05-232.3%[0%, 46%]
d72026-05-2917.3%[0%, 82%]
d142026-06-0524.5%[0%, 93%]
d302026-06-218.0%[0%, 86%]
Spotlight countries