Benchmarks
The results behind each suggestion, by bookmaker and league.
Which direction has worked in each cell?
Compare normal and reversed one-unit returns for each bookmaker, market and league.
3Cells with a direction
76Cells still gathering evidence
10Earlier matches required
79Cells in this selection
1–3 of 3 cellsOne unit per earlier signal · returns rounded to two decimals
| Bookmaker / league | Original model signal | Earlier matches | Normal | Reversed | Selected direction |
|---|---|---|---|---|---|
| PinnacleLigue 1 | Goals · UnderMatch totalEvidence13 reconstructed · 0 recordedtotal_goals · thestatsapi | 13 | −4.47u-34.4% ROI | +2.53u19.5% ROI | Reverse → OverHigher earlier return |
| Betfair ExchangeLigue 1 | Goals · OverMatch totalEvidence11 reconstructed · 0 recordedtotal_goals · thestatsapi | 11 | +18.00u163.6% ROI | −0.85u-7.7% ROI | Normal → OverHigher earlier return |
| Betfair ExchangeLigue 1 | Goals · UnderMatch totalEvidence11 reconstructed · 0 recordedtotal_goals · thestatsapi | 11 | −11.00u-100.0% ROI | +0.54u4.9% ROI | Reverse → OverHigher earlier return |
How to read this evidence
A cell needs 10 distinct earlier matches. Higher return selects normal or reversed, including the smaller loss. This qualifies a direction for monitoring; lineup, contract and current-edge checks follow.
Reconstructed history is labelled separately from genuinely recorded pre-match signals. Published prediction returns have their own record. VIP and Free are assigned after confirmation.
Release 20261019-live-v4 · measured 19/10/2026, 14:53:49