Every prediction. Accounted for.

1. 1
   Rate

   A surface-specific Elo, trained match by match against every ATP result since 2020, plus tour-level Challenger and qualifying. Hard, clay and grass each carry their own rating, weighed against recent form and the head-to-head record on the surface in play.

2. 2
   Price

   That win probability becomes a fair decimal price. We line it up against the best price on offer across the sportsbooks, with the book's built-in margin stripped out so the comparison is honest.

3. 3
   The gap

   Where our price and the market's disagree by more than 5%, we publish the match and show both numbers. A gap is a disagreement, not a prediction that we are the one who is right. Above 15% it usually means the model cannot see something, like an injury or a walkover, so treat a large gap as a reason to look rather than a reason to bet.

• Nota guarantee. A gap between our number and the price is a disagreement, not a demonstrated profit. Measured against the market's own number, the price predicts results at least as well as we do. It says nothing about any single match.
• Notfinancial advice. Bet what you can lose, track everything, never chase.
• Nota tout service. Matches surface because the numbers disagree, not because we like a player.

One person builds and runs CourtCockpit, which is why the model says what it does and why the record is published with the losses in it. Questions, billing, or something broken: support.