voidly
Multi-horizon shutdown forecast

Bangladesh — three honest horizons

How shutdown risk for Bangladesh evolves over 1 day, 7 days, and 30 days. Each horizon uses its own XGBoost model with per-horizon SHAP attribution and a 90% conformal interval.

Generated 2026-05-21 12:50 UTC · model multi-horizon-h-v1 · raw JSON

Probabilities

1 day
1d
27.1%
90% interval [21%, 34%]
7 days
7d
58.8%
90% interval [46%, 71%]
30 days
30d
70.0%
90% interval [20%, 100%]

Consistency check

OK — monotonicP(1d) ≤ P(7d) ≤ P(30d)

The three horizons are internally consistent: longer windows capture at least the risk of shorter windows. This is the expected behavior — a 30-day window must contain any 7-day or 1-day shutdown.

27.1% ≤ 58.8% ≤ 70.0%

Top-5 SHAP features per horizon

Each horizon has its own learned drivers. Positive SHAP values push the prediction up; negative values push it down. Features differ across horizons because near-term risk responds to acute signals, while month-out risk responds to slower structural factors.

HorizonRankFeatureSHAP
1-day#1week_of_year-0.837
#2risk_tier-0.266
#3block_rate_lag3+0.176
#4day_of_week-0.174
#5recent_shutdown+0.143
7-day#1week_of_year-0.788
#2risk_tier-0.432
#3block_rate_roll7_mean+0.298
#4recent_shutdown+0.164
#5month-0.140
30-day#1week_of_year-1.172
#2risk_tier-0.546
#3gdelt_unrest_30d+0.315
#4block_rate_lag1+0.244
#5recent_shutdown-0.124

Honest caveats

  • Each horizon is a separate XGBoost model with its own features and its own honest evaluation. LOCO AUC across spotlight countries: 1d 0.91 · 7d 0.88 · 30d 0.84.
  • 30-day forecasts inherently have wider conformal intervals (more time = more uncertainty). A wide interval is not a bug — it's honesty.
  • These numbers are not guarantees. A 70% probability does not mean a shutdown is certain; a 20% probability does not mean you're safe.
  • See /atlas/multi-horizon for the cross-country index, or /atlas/models for the full model registry.

Related