Experimental AI-assisted analytics — predictions and ratings are estimates, not official results.

Accuracy Report

Every prediction is graded against the actual result using a strict chronological walk-forward — Chronological walk-forward: each match is predicted using only matches completed before it (warm-up of 6 qual matches per event). No final rankings or later results leak into a prediction.

Experimental, AI-assisted analytics

predictFRC uses AI-assisted experimental analytics. Predictions, rankings, ratings, and insights are not guaranteed to be accurate and should not be treated as official results or professional advice. Data may be incomplete, delayed, miscategorized, or incorrect. predictFRC is a new project under active development, and accuracy will improve over time.

Model apex-0.2.0 · 12072 predictions across 186 events · 2026-03-03 → 2026-06-29

Winner accuracy
77%
Score MAE
53.56725190523501pts
Brier
0.16139022723322488
Calibration (ECE)
0.051326994173824005

Confidence calibration

When APEX says 70%, does the favorite win ~70% of the time? Closer bars = better calibrated.

Stated confidenceActual win rateSample
50–60%
59%
3405
60–70%
72%
2831
70–80%
84%
2404
80–90%
91%
1943
90–100%
97%
1489

Baseline comparison

APEX vs naive predictors on the same matches.

50 / 50 coin flip49%
Better win-loss record66%
Higher rank (by record)66%
Recent-performance average70%

Where the model was most wrong

High-confidence predictions that missed.

Qualification 56Favored Red at 98% — Blue won2026NEW
Qualification 41Favored Blue at 98% — Red won2026CUR
Qualification 14Favored Blue at 96% — Red won2026PABEN
Qualification 103Favored Blue at 96% — Red won2026DAL
Qualification 49Favored Red at 96% — Blue won2026GAL
Qualification 27Favored Red at 96% — Blue won2026MABOS
Qualification 31Favored Blue at 95% — Red won2026JOH
Qualification 48Favored Blue at 95% — Red won2026CUR
Qualification 40Favored Red at 95% — Blue won2026MIBER
Qualification 69Favored Blue at 95% — Red won2026MABOS

Model limitations

Small samples early

Week 1 ratings rest on very few matches and swing the most. Confidence scores reflect this.

Cold-start teams

Teams with no current-season matches use heavily-regressed provisional estimates with wide uncertainty.

Rare events

Mechanical failures, no-shows, and unusual fouls are hard to predict and inflate score error.

Regression to the mean

APEX deliberately discounts single lucky/unlucky matches, so it can lag a genuine breakout for a match or two.

predictFRC does not claim its predictions are guaranteed. Accuracy improves as more data arrives and the model is refined.