voidly
TR · per-country backtest

Turkey forecast vs reality

Every Voidly Sentinel shutdown-risk forecast for Turkey, plotted against what actually happened. 28 (predicted, observed) pairs from the rolling 30-day evaluation window.

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

Forecasts evaluated
28
since Apr 17
Accuracy @ 0.5
32.1%
9/28 correct
Brier score
0.517
lower is better
Observed positive rate
57%
mean predicted 6%

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 17May 14

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

All 28 predictions (newest first)

Eval dateForecastPred ≥ 0.5?Observed?Correct?
May 146.9%no event
May 138.5%no event
May 127.1%no event
May 118.2%no event
May 105.9%no event
May 97.9%no event
May 86.1%no event
May 76.1%no event
May 66.8%no event
May 57.0%no event
May 45.3%no event
May 36.3%no event
May 26.6%shutdown
May 16.5%shutdown
Apr 307.0%shutdown
Apr 297.0%shutdown
Apr 287.0%shutdown
Apr 275.2%shutdown
Apr 266.6%shutdown
Apr 255.6%shutdown
Apr 244.6%shutdown
Apr 232.6%shutdown
Apr 223.3%shutdown
Apr 214.0%shutdown
Apr 203.2%shutdown
Apr 193.5%shutdown
Apr 185.2%shutdown
Apr 173.7%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