Sun 15 Nov
We compare every book’s price against the fair price set by the rest of the market. When one book is long, we publish it: the book, the price, the fair price, and the price not to take below.
Free to read once a game starts. Members see each signal the moment it posts.
Free includes the model’s projected line on every game. No card.
Includes 64 scorer signals, whose closing-line value is partly a product of how their fair price is built (method-affected).
Signals before 13 November were the same scan’s alerts, posted in real time to the operator and graded at the posted price, at the seven Illinois books.
A signal publishes with the book, the price, our fair price, and the price not to take below.
Over 22.5 points — example player
It reaches you by push notification or Slack DM, at the books you chose.
Placed or Placed at… records your bet at your price and stake. Pass hides it, with a reason — the same ones as in Slack.
My bets follows it live, through the game.
Every signal is graded at the price we published and against the closing line, win or lose — and the record keeps all of them.
No source is trusted on reputation. Each is scored against real outcomes, market by market, and one that cannot beat the category average is dropped to zero weight rather than quietly averaged in. Agreement is not evidence — five forecasters can be wrong together.
Probabilities are built from measured error: the uncertainty on a market is sized from how far its projections actually land from the result.
Every race is modelled on the history of that track and surface — a dirt sprint is not scored on turf routes run somewhere else. The model learns finish order directly, ranking a field rather than rating horses in isolation, and reads form as it stood on race day.
Exotics are priced off the whole field, correcting for the fact that a horse’s chance of running second is not simply its chance of winning — skipping that step is what makes naive exotic prices look better than they are.
The model’s projected score, spread and total on every game, live odds from the books we cover, live tote prices on every race, and the entire graded record. Permanently, not as a trial.
No promised return, no win rate. Those are the claims that draw regulators, and the ones you would have to keep proving every month. The measurement is the product.
Every settled bet is on the record page with the price it was graded at, win and loss alike. Read it, and read the method before you read the price.
Cyprus
Montenegro
Latvia
Armenia
Finland
San Marino