voidly
BR · per-country backtest

Brazil forecast vs reality

Every Voidly Sentinel shutdown-risk forecast for Brazil, 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
78.1%
57/73 correct
Brier score
0.009
lower is better
Observed positive rate
0%
mean predicted 5%

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 283.3%—no event✓
Jun 276.2%↑no event✗
Jun 265.2%↑no event✗
Jun 255.6%↑no event✗
Jun 244.9%—no event✓
Jun 233.7%—no event✓
Jun 225.0%↑no event✗
Jun 213.7%—no event✓
Jun 205.4%↑no event✗
Jun 194.9%—no event✓
Jun 184.5%—no event✓
Jun 174.3%—no event✓
Jun 164.9%—no event✓
Jun 155.2%↑no event✗
Jun 143.4%—no event✓
Jun 133.7%—no event✓
Jun 123.6%—no event✓
Jun 113.6%—no event✓
Jun 104.0%—no event✓
Jun 93.9%—no event✓
Jun 84.8%—no event✓
Jun 73.8%—no event✓
Jun 65.0%↑no event✗
Jun 53.8%—no event✓
Jun 44.7%—no event✓
Jun 34.4%—no event✓
Jun 24.7%—no event✓
Jun 14.0%—no event✓
May 315.4%↑no event✗
May 303.9%—no event✓
May 294.8%—no event✓
May 283.2%—no event✓
May 273.7%—no event✓
May 263.8%—no event✓
May 254.7%—no event✓
May 244.9%—no event✓
May 234.2%—no event✓
May 223.0%—no event✓
May 2169.8%↑no event✗
May 204.0%—no event✓
May 195.4%↑no event✗
May 184.7%—no event✓
May 174.1%—no event✓
May 164.7%—no event✓
May 154.9%—no event✓
May 144.4%—no event✓
May 133.2%—no event✓
May 124.5%—no event✓
May 114.3%—no event✓
May 105.3%↑no event✗
May 93.0%—no event✓
May 84.4%—no event✓
May 73.4%—no event✓
May 65.2%↑no event✗
May 53.2%—no event✓
May 44.6%—no event✓
May 34.7%—no event✓
May 23.4%—no event✓
May 14.5%—no event✓
Apr 303.7%—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