What happens before 9 AM
Every night the model ingests the data, simulates each game, compares to the market, and publishes only the edges.
Ingest — 11 million data points
Every night the model pulls everything that moves a line: who's playing, how they've played, and how the market is pricing it — across 40+ sportsbooks.
Simulate — every game, 10,000 times
Each matchup runs through Monte Carlo simulation — 10,000 full plays of the game with the night's actual conditions. The output isn't a prediction of who wins; it's a probability distribution: how often each side covers, how often the total goes over, and from that, our own fair price for every line on the board.
Compare — find where the market is wrong
Our price gets compared against the best available market price. Agreement means no bet — the market is right most of the time. A pick only exists when the gap clears our edge threshold and survives a sanity layer that checks for stale data and news the model might be missing.
Publish — timestamped, then graded
At 9 AM ET every pick goes out with its confidence, edge, unit size, the worst price worth taking, and the reasoning in plain English. Each one is timestamped on the public ledger before the games start, and graded after the final — wins, losses, everything.
What the model gets wrong
Late news moves lines after we publish, thin-data spots are noisier, and variance is real — a 62% model still loses four times in ten. We publish the losses anyway.
Picks publish at 9 AM. A star scratched at 6 PM can invalidate the math. That’s why every pick carries a "play to" price — if the line has moved past it, the edge is gone and you should pass.
Season openers, rookie debuts, post-trade rosters — when history is thin, simulations are guesses wearing math. The sanity layer suppresses most of these spots, which is why some nights we send 4 picks, not 12.
A 62% model still loses 4 bets in 10 — and sometimes loses them in a row. We’ve had losing months, and every one of them is on the public ledger. If a cold week would break your bankroll, bet smaller. The math only works over volume.
The skeptic's questions
If the model works, why sell it instead of just betting it?
We do bet it — the picks are placed before they're published, which is also why publishing costs us nothing. But sportsbooks limit winning accounts fast, which caps how much a model can earn betting alone. Subscriptions scale; our bet sizes can't. Both revenue streams point the same direction: the model has to keep winning.
Won't the edge disappear if thousands of people bet the same picks?
Lines do move when our subscribers bet — that's why every pick includes the worst price worth taking. If you get there late and the number is past it, the correct play is no play. Our edge comes from a repeatable process, not from any single line staying soft.
Couldn't you fake the track record?
That's exactly why every pick is timestamped publicly before the game starts. A record you publish after results come in is marketing; a record timestamped before tip-off is evidence. Check the ledger yourself — the losses are right there.
Is this legal?
Yes. We're a sports analytics publisher — we don't take bets, hold your money, or operate as a sportsbook. Whether and where you bet is up to you and your local laws; we're for users 21+ in places where sports betting is legal.
Watch the pipeline work.
The model's highest-edge play lands in your inbox at 9 AM tomorrow. Free, every day.
Get today's free pick →