A price, an opinion, and the gap between them.
Every bet on this site is the same three steps. The market posts a number. A model produces its own — blended from more than a dozen independent forecasters, each weighted by how accurate it has actually been. Where the two disagree by enough to survive the vig, that gap is the bet, stated as a percentage of what you stake rather than as a pick.
Then the part most of this category leaves out: every published call is graded once the result is in, and the grades stay up. Everything below is that idea in more detail, including the parts that are unflattering.
Where the numbers come from
Projections are collected from more than a dozen independent forecasters and blended into a single number for every game, player and race. The blend is not an average. No source is trusted on reputation. Each one is scored against real outcomes, market by market, and a forecaster that cannot beat the category average is dropped to zero weight rather than quietly averaged in.
Agreement between sources is not treated as evidence either. Five forecasters can be wrong together, and a market where everyone agrees is a market where a single shared assumption is doing all the work.
That number is then priced against the live market — the same market a reader can actually bet into — and what this site publishes is the disagreement, not the forecast on its own.
Probabilities built from measured error
A projection is a point; a bet needs a distribution. We track how far each market’s projections actually land from the result and size the uncertainty from that spread, instead of a constant chosen once and left alone. A market the model reads well earns a tighter distribution than one it reads badly, and the difference shows up in the rating rather than being smoothed away.
Where a market’s outcomes run wider than a simple count model allows, we use a distribution that fits — but only where the evidence earns the change. Coverage runs across NFL, NCAA FB, NBA, WNBA, NCAA MBB, NCAA WBB, MLB, NHL and Soccer; game lines, totals, team totals and player props.
Hit rate, closing line value and calibration are tracked market by market and published, including the places the model has been wrong. That is the whole argument for it: a model that is never scored is just an opinion with a decimal point.
The racing model is a different animal
Every race is modelled on the history of that track and that 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, across speed and class figures, pace shape and running style, post position, and the recent form of the jockey, the trainer, and the two of them together.
Form is read as of race day. When the model is tested against last season it sees only what was knowable at the time, so a good backtest cannot be an artefact of hindsight — which is the most common way a racing model flatters itself.
Exacta, trifecta and superfecta prices are built from the same field, using the long-established correction 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 far more attractive than they are.
Many books, and only the ones you can use
The same bet is priced differently everywhere, and the difference is the whole game. A spread at −108 at one book and −118 at another is a positive bet at the first and a negative one at the second. Every board here shops the books you have selected and shows the best price among them, with the operator named on the row.
A new account starts on 5 national books and can change that in a click. The full list is here — sixteen operators, including two prediction exchanges, which price the same events differently.
The rating, 1 to 5
Expected value alone is not confidence. A big edge on a market the model knows little about is worth less than a small edge on one it knows well, so every bet carries a rating that combines the size of the edge with how much the model trusts itself on that market.
- 4–5 — a large edge the model is confident in. A handful a week.
- 3 — real but modest. The bulk of what gets published.
- 1–2 — a low edge, low confidence, or both. Shown, not recommended.
The bar never moves to fill a quiet day. Some Tuesdays nothing rates above a 2, and the board says so rather than promoting the best of a bad slate.
What this is not
- No promised return, no edge over the market, no win rate. Not because they would be hard to write, but because they would have to be re-proved every month — and the measurement is the thing that stays true on a losing week.
- There is no bet slip and no button that places anything. We do not hold money, and there are no affiliate links on a price.
- No lock of the day, no free pick, no capper theatre. Every bet the model rates is published and graded, whatever it does.
- This is research rather than advice. The model is wrong often enough that treating it as advice would be a mistake, which is why the record is free and the losses are in it.
The record, in full
Every bet rated 4 and above — the calls the model stands behind — Sun 30 Aug to Fri 4 Sep. Graded at the last price recorded before the game. The 3s are published too, on the record page.
This is the live figure, not a screenshot. Read the whole record — every settled bet, win and loss, with the price each was graded at.
Two tiers
Free is not a trial and does not expire. It is the model’s lines on everything, permanently — enough to check the projections against results before paying for the scoring.
- Projected score, spread and total on every game
- Live odds from the books you pick
- Every race card, with live tote prices and results
- The full track record and every graded bet
- The day’s slate, in start-time order
- Everything in Free
- Win probability, EV and a rating on every bet
- The whole slate, ordered by value
- Player props, priced across every book
- The racing model: win probability and priced exotics
- A recommended stake on every bet
Odds from every book we cover, refreshed continuously, and the compute to reprice every market against them. That cost scales with coverage rather than with subscribers, which is why there is one paid tier and not three.
There is no enterprise plan, no API upsell and no tier that unlocks a better model. Every member sees the same numbers at the same time.
Questions we get
Do I need accounts at every book?
No. Most people have two or three. Every price shown is the best among the books this site covers, and the book offering it is named on the row — so you can see at a glance whether a bet is one you could actually take.
How many bets a day should I expect?
It varies with the calendar rather than with a target. A full Saturday produces far more than a quiet Tuesday, and on some days nothing rates above a 2. The count is a consequence of the market, and the board says when there is nothing worth showing.
How long is the record?
617 settled bets, Sun 30 Aug to Fri 4 Sep. That is short — long enough to see a shape, not long enough to be certain of one — and the record page says so beside the figure rather than in a footnote.
Can I see a bet before I subscribe?
You can see the model’s projected line on every game with a free account, and all of the graded record without one. What Member adds is the scoring — the probability, the expected value, the rating and the ordering — on everything.
Is this gambling advice?
No. It is research: prices, projections and a published record. What you do with it is yours, and the model is wrong often enough that treating it as advice would be a mistake.
Start with the record, not the pitch.
Every graded bet is on one page, free, win and loss alike. Read it first and decide whether the forecasts are worth $35 a month.