The record
Every data lean we publish is logged before kickoff — the probability, the market odds at that moment, immutably — and settled after full time at flat 1-unit stakes. Wins and losses alike. The market is usually right; this page is where we prove we're honest about it.
20
Leans logged
0
Decided
—
Hit rate
+0.00u
P/L · flat 1u
20
Pending
By market
| Market | Decided | Won | Hit rate | P/L |
|---|---|---|---|---|
| Half-time Over/Under 1.5 | 0 | 0 | — | +0.00u |
| Full-time Over/Under 2.5 | 0 | 0 | — | +0.00u |
DC v2 backtest — 2024-2025 / 2025
backtest, not the live recordWhat our score-distribution model's blind leans (divergence ≥ 2% vs closing odds, flat 1-unit stakes) would have returned last season across 9 leagues. Spoiler: they lose — -97.4u over 3,036 leans — which is precisely why we publish probabilities, not tips. The probabilities themselves are well calibrated (table below); the market's margin is what eats the difference. The live ledger above only ever contains leans logged before kickoff.
3,036
Backtest leans
47.8%
Hit rate
-97.4u
P/L (flat 1u)
2.17
Avg odds
Calibration — predicted probability vs what actually happened
| Predicted | Actual | Samples |
|---|---|---|
| 10%–20% | 19.5% | 82 |
| 20%–30% | 30.3% | 1080 |
| 30%–40% | 36.9% | 2285 |
| 40%–50% | 44.7% | 2730 |
| 50%–60% | 55.3% | 2730 |
| 60%–70% | 63.1% | 2285 |
| 70%–80% | 69.7% | 1080 |
| 80%–90% | 80.5% | 82 |
How this works
- Every published probability is snapshotted before kickoff together with the market odds at that moment. Records are never edited afterwards.
- Settlement is mechanical: flat 1-unit stakes, won = odds − 1, lost = −1, postponed or unresolvable = void (0).
- The probabilities are a statistical baseline built from historical first-goal-time and scoring data — they know nothing the market doesn't. This page exists so you can see exactly what that is and isn't worth.
- Statistics, not betting advice. 18+ · never stake more than you can afford to lose.