Track record
Walk-forward backtest
Every prediction the model has ever made, settled. $100 staked per pick at fair odds (1/argmax_prob). This is the optimistic bound — a real book charges vig that drags ~5-8% per leg, so flat-positive here is required just to break even at a sportsbook.
Sample: 2022-01-03 → 2026-08-30 · 30,000 predictions
Walk-forward floor vs live model
Walk-forward is Elo-only — the lowest defensible model. The live model adds Platt calibration, news features, and market-blended priors. This is a true same-match comparison: BOTH rows are computed over the 734 matches where each model made a graded prediction — so the Δ is the signal the extra stack actually adds, not an artefact of different match sets.
Shared matches- Elo only
- 734
- Live model
- 734
- Δ
- —
Argmax hit- Elo only
- 54.0%
- Live model
- 54.1%
- Δ
- +0.1pp
ROI (fair odds)- Elo only
- -2.79%
- Live model
- -5.72%
- Δ
- -2.93pp
Overall (fair odds)
Predictions
30,000
argmax avg 62.7%
Argmax hit rate
61.7%
18,498 of 30,000
Net P/L @ $100/pick
−$44,530
staked $3,000,000
ROI
-1.48%
fair-odds — book vig drags ~5-8% per leg
By sport
Tennis-1.75% roi
- Predictions
- 23,672
- Argmax hit
- 62.8%
- Avg prob
- 64.0%
- Staked
- $2,367,200
- Returned
- $2,325,794
- Net
- −$41,406
Football3.19% roi
- Predictions
- 3,898
- Argmax hit
- 51.4%
- Avg prob
- 49.4%
- Staked
- $389,800
Reading this honestly
- Fair-odds backtest uses 1/argmax_prob as the decimal price. Real books charge vig — a fair-odds ROI of +5% corresponds to roughly -3% at a real sportsbook. So the realised number here is the optimistic bound, not what you'd actually win.
- Walk-forward = Elo only. No Platt blending, no news, no market signal — predictions captured BEFORE the Elo update on each match. This is a strict lower bound on the live model's quality.
- Argmax bias.The model picks its most-likely outcome. In football that's usually the home team at short odds — the market's most efficient band. ROI ≈ 0% there is honest calibration; meaningful upside would require beating the close in those bands — which is measured directly here.
- Why this beats small-sample. The daily-tickets track record needs ~30 graded tickets per tier before signal stabilises. This page covers thousands of predictions across multiple seasons — the variance question is settled here, not on a 5-ticket sample.