voidly
JP · per-country backtest

JP forecast vs reality

Every Voidly Sentinel shutdown-risk forecast for JP, plotted against what actually happened. 12 (predicted, observed) pairs from the rolling 30-day evaluation window.

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

Forecasts evaluated
12
since May 21
Accuracy @ 0.5
0.0%
0/12 correct
Brier score
0.577
lower is better
Observed positive rate
0%
mean predicted 75%

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 0.50May 21Jun 1

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

All 12 predictions (newest first)

Eval dateForecastPred ≥ 0.5?Observed?Correct?
Jun 183.0%↑no event✗
May 3178.2%↑no event✗
May 3066.6%↑no event✗
May 2984.0%↑no event✗
May 2866.8%↑no event✗
May 2787.4%↑no event✗
May 2679.3%↑no event✗
May 2570.6%↑no event✗
May 2465.4%↑no event✗
May 2379.0%↑no event✗
May 2246.4%↑no event✗
May 2193.3%↑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