Track Record
Every pick from the EdgeLab 4.2 model, locked in before the match at the Bet365 odds of the moment. Results published as they come, nothing is ever rewritten.
September 2026-3.46u
August 2026+5.85u
July 2026+11.69u
June 2026-6.86u
May 2026+1.57u
April 2026-3.25u
March 2026-1.37u
February 2026+3.72u
January 2026+12.40u
BACKTEST · SIMULATIONThe model, validated over ten years (2016-2025)
The current model replayed over 49,645 priced ATP matches (real historical odds), under the exact rules of the site: official scope (strong + moderate value · odds < 1.80) and stakes 2 u / 1.5 u. No pick was published during that period: this is a retrospective simulation, reproducible from the code, that validates the method; the proof under real conditions is the track record above, which applies those same rules live.
Loading the list…
BACKTEST · SIMULATIONThe model on the WTA, validated over ten years (2016-2025)
The same model, replayed over 52,048 priced WTA matches (real historical odds), under this tour's own scope (all three levels · odds < 1.80) and the same stakes 2 u / 1.5 u / 1 u. On this tour, slight value signals do count: +7.8% with nine positive years out of ten. No pick was published during that period: a retrospective simulation, reproducible from the code.
Loading the list…
Going further: CLV and official scope
CLV compares our odds at pick time to the market's closing odds. Beating the close consistently is the most reliable sign of a model that sees ahead of the market, long before ROI can tell. On our markets the line often barely moves: matching the close is the most common case, and losing it is the real warning sign. It's our #1 KPI, detailed in the methodology.
Edge: the gap between the model's probability and the one contained in the odds, bookmaker margin removed. A pick is only issued when that gap clears our thresholds: value has to stay rare.
Official scope (strong + moderate on ATP, all three on WTA · odds < 1.80): only these picks count toward the record. The choice comes from ten years of backtesting (49,645 matches): returns rise as odds shorten, and each circuit keeps only the levels that win there. A rule only applies going forward: every pick stays counted under the scope announced at capture, and whatever leaves the record remains displayed and settled.
Staking: 2 u (strong) / 1.5 u (moderate) / 1 u (slight, observation), a backtest-validated sizing kept flat for readability. Pro members also see, on every official pick, the suggested quarter-Kelly stake as a % of bankroll, for reference.
Voided (market reversal): if the match favorite flips at our reference bookmaker before first serve (a move of at least 8 probability points), the signal is voided and timestamped: such a move almost always reflects information the stats can't see yet (injury, physical issues, or something else). The line stays displayed, outside the record and CLV. The rule is symmetric, whether the market moves with us or against us.
If the market unanimously turns one of our picks around before the match (say 1.53 to 2.20 everywhere within a few hours, as with Martineau at the Bonn Challenger), the signal is automatically voided and stays displayed as such. A move like that almost always reflects information the stats cannot see yet: injury, poor fitness, withdrawal. Rather than let you follow a polluted bet, we void it before the match, in the open. Nothing is deleted, everything stays visible.
Today's picks are for members
The picks BEFORE the match, the model's probability and the analysis behind it.Everything already settled stays public, right here, untouched. Pro adds the picks BEFORE the match, the model's probability and the analysis behind it.
€19.99/month
instead of €24.99 · founder rateinstead of €24.99 · founder rate locked in for life
No commitment, cancel onlineNo commitment · cancel online · payment by Stripe
The stat of the day
Every morning, one number that changes how a match reads: the most striking of the day, from the biggest tournament. Nothing else.
One email per morning, one-click unsubscribe. Your address is used for this and nothing else, and never shared.