voidly
TH · per-country backtest

Thailand forecast vs reality

Every Voidly Sentinel shutdown-risk forecast for Thailand, 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
50.7%
37/73 correct
Brier score
0.289
lower is better
Observed positive rate
29%
mean predicted 7%

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 281.8%no event
Jun 271.6%no event
Jun 261.9%no event
Jun 251.7%no event
Jun 241.8%no event
Jun 231.8%no event
Jun 221.8%no event
Jun 213.6%no event
Jun 205.1%no event
Jun 193.3%no event
Jun 183.0%no event
Jun 175.0%no event
Jun 164.6%no event
Jun 155.7%no event
Jun 145.1%no event
Jun 132.8%no event
Jun 122.9%no event
Jun 115.0%no event
Jun 102.8%no event
Jun 95.4%no event
Jun 85.0%no event
Jun 75.5%no event
Jun 65.3%no event
Jun 55.0%no event
Jun 45.4%no event
Jun 33.8%no event
Jun 24.5%no event
Jun 13.7%no event
May 313.8%shutdown
May 304.5%shutdown
May 295.1%shutdown
May 284.6%shutdown
May 273.8%shutdown
May 264.9%shutdown
May 255.7%shutdown
May 2477.1%no event
May 2378.4%no event
May 2218.1%no event
May 2169.4%no event
May 206.8%no event
May 197.8%no event
May 1817.6%no event
May 174.8%no event
May 164.6%no event
May 155.1%no event
May 144.3%no event
May 134.4%no event
May 124.4%no event
May 114.4%no event
May 104.9%no event
May 95.1%no event
May 83.9%no event
May 73.3%no event
May 64.8%no event
May 53.9%no event
May 45.3%no event
May 34.0%no event
May 24.2%shutdown
May 13.8%shutdown
Apr 303.0%shutdown

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