voidly
SD · per-country backtest

Sudan forecast vs reality

Every Voidly Sentinel shutdown-risk forecast for Sudan, plotted against what actually happened. 73 (predicted, observed) pairs from the rolling 30-day evaluation window.

Updated every 30 min · CC BY 4.0 · Raw JSON · Current forecast →

Forecasts evaluated
73
since Apr 17
Accuracy @ 0.5
67.1%
49/73 correct
Brier score
0.096
lower is better
Observed positive rate
10%
mean predicted 18%

Forecast time series

Blue line: forecast probability. Green ✓ markers: forecast was right. Red ✗ markers: forecast was wrong. Dashed line at 0.5 is the binary decision threshold.

0.000.250.500.751.00threshold 0.50Apr 17Jun 28

Y axis: forecast probability · Faint tick: distance to observed outcome (0 or 1)

All 73 predictions (newest first)

Eval dateForecastPred ≥ 0.5?Observed?Correct?
Jun 2866.4%no event
Jun 2766.4%no event
Jun 2666.4%no event
Jun 2570.1%no event
Jun 2470.1%no event
Jun 2378.4%no event
Jun 2275.2%no event
Jun 214.2%no event
Jun 205.4%no event
Jun 196.1%no event
Jun 185.5%no event
Jun 174.9%no event
Jun 165.2%no event
Jun 155.1%no event
Jun 143.3%no event
Jun 134.2%no event
Jun 124.5%no event
Jun 114.9%no event
Jun 105.6%no event
Jun 94.6%no event
Jun 84.1%no event
Jun 75.3%no event
Jun 65.1%no event
Jun 53.3%no event
Jun 44.7%no event
Jun 35.0%no event
Jun 25.2%no event
Jun 14.9%no event
May 3145.2%shutdown
May 3044.4%shutdown
May 2948.1%shutdown
May 2848.0%shutdown
May 2745.5%shutdown
May 2661.7%shutdown
May 2561.0%shutdown
May 2460.1%no event
May 2379.1%no event
May 2217.6%no event
May 2182.0%no event
May 205.3%no event
May 197.2%no event
May 187.2%no event
May 174.3%no event
May 164.5%no event
May 153.8%no event
May 144.2%no event
May 134.6%no event
May 123.1%no event
May 114.2%no event
May 104.0%no event
May 94.1%no event
May 84.8%no event
May 75.2%no event
May 64.7%no event
May 54.6%no event
May 45.1%no event
May 34.5%no event
May 24.8%no event
May 14.5%no event
Apr 305.1%no event

How to read this

  • Each row is one historical forecast. We made the prediction at eval_date, then waited the 7-day horizon, then graded against the observed outcome.
  • Forecast % is the calibrated probability we published that day. Post-recalibration (2026-05-20) these now match actual observed rates much better — see the refit finding.
  • Pred ≥ 0.5 shows the binary alert decision. Note we usually fire alerts at a lower threshold (see /v1/sentinel/global_heatmap for the live cutoff) — the 0.5 column here is for backtest scoring consistency with the global confusion matrix.
  • Correct = both (pred ≥ 0.5) and (observed) agree.

Related