voidly
Multi-horizon shutdown forecast

Belarus — three honest horizons

How shutdown risk for Belarus 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 12:51 UTC · model multi-horizon-h-v1 · raw JSON

Probabilities

1 day
1d
15.1%
90% interval [2%, 28%]
7 days
7d
58.8%
90% interval [34%, 84%]
30 days
30d
70.0%
90% interval [29%, 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.

15.1% ≤ 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-0.769
#2risk_tier-0.179
#3block_rate_roll7_mean-0.133
#4day_of_week-0.091
#5block_rate_roll30_mean-0.084
7-day#1week_of_year-0.465
#2block_rate_roll7_mean+0.359
#3blocked_count_roll7_mean+0.163
#4month-0.138
#5block_rate_roll7_std-0.086
30-day#1week_of_year-0.853
#2gdelt_unrest_30d+0.320
#3block_rate_lag1+0.278
#4month-0.247
#5recent_shutdown-0.143

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