voidly
7-day shutdown forecast · calibrated

Tanzania8% peak risk

Calibrated via isotonic refit on 810 live outcomes (2026-05-20). See calibration drift → · Tanzania country profile →

The Voidly Sentinel model forecasts a peak shutdown probability of 7.5% for Tanzania over the next 7 days, with the highest risk on day 2 (Sat, May 23). Average risk across the window: 7%.

90% conformal interval: [0%, 43%]empirical coverage 90.4% (target 90%).

Per-day risk

0%25%50%75%100%7%Thu4%Fri8%Sat6%Sun6%Mon6%Tue7%Wed7%Thu

Dashed line: 50% threshold. Bars colored by risk band.

Per-day drivers

DateRiskDrivers
Thu, May 217% · Lowno drivers
Fri, May 224% · Lowno drivers
Sat, May 238% · Lowno drivers
Sun, May 246% · Lowno drivers
Mon, May 256% · Lowno drivers
Tue, May 266% · Lowno drivers
Wed, May 277% · Lowno drivers
Thu, May 287% · Lowno drivers

What drove the prediction

Top features by signed contribution to today's risk score. Positive (↑) features push the prediction higher; negative (↓) features push it lower.

  • gdelt_unrest_30d-0.041
  • critical_incident_7d+0.020
  • block_rate_roll7_mean-0.018

Similar past event

The model found a similar event in the corpus. Reading the incident report tells you what “8% risk for Tanzania” looked like when it actually happened.

TZ-2026-0051critical

disruption in TZ · Sun, May 17

Recent evidence

Live measurements from upstream networks supporting this forecast. Click any link to view the raw data on the source.

Honest caveats

  • The model's base AUC on a time-based holdout is 0.50 (random on novel events). LOCO median AUC is 0.91. The calibrated number you see above is the most-honest operational figure but it's NOT a guarantee.
  • Calibration was refit on 2026-05-20 on 810 live outcomes — it's good for the 30 watched censoring countries but will drift if the world changes. Nightly recalibration runs at 04:30 UTC.
  • A 70% forecast doesn't mean a shutdown is guaranteed; a 20% forecast doesn't mean it's safe. The 90% conformal interval is the honest uncertainty band.
  • For long-form methodology see /methodology and the calibration refit finding.

Model version: v1@2026-05-21T04:20:38.966951

Related