How to read GameTime Picks
A 2-minute guide for everyone — no betting background needed. Everything here is educational and paper-only: there are no real wagers, just hypothetical paper tracked honestly.
Start here
The numbers on a card
Our model's estimate of how likely an outcome is — e.g. “Model 56%” means the model thinks it happens 56 times out of 100.
The same chance implied by the sportsbook's price (the odds), stripped of the book's margin. It's the “crowd’s” estimate.
The gap between the two: Model − Market. A positive edge means the model rates the pick higher than the market prices it. Small edges are normal; big edges often mean thin data, not a free lunch.
Shown American-style: −150 means risk 150 (paper) to win 100; +130 means risk 100 to win 130. Combine legs and the odds multiply.
Risk tiers
The three tools
Every market the model has a read on — shown with model %, market %, and edge. A “projection view” is information; not every view is suggested as a card.
The model's actual paper picks for the day, bundled into cards by risk tier. Enter any stake to see the projected paper return. Browse them all on Picks.
Make your own paper card from eligible legs across sports on Build — add legs, set a stake, and see the combined odds + payout live.
Bank Builder
A transparent paper ladder: one disciplined pick per rung, compounding a starting bankroll toward a target. It only advances when a genuinely eligible low-risk card clears strict gates — when nothing qualifies, it waits rather than forcing a pick. Track it on Bank Builder. Paper-only, for education.
By sport
90-minute regulation only — a Draw is a real third outcome (no extra time/penalties). Double chance, total goals/corners, and player props (labeled lineup-pending until lineups post).
Player-prop projections — pitcher strikeouts, batter hits / total bases — from game logs vs the line, plus optimizer suggested cards.
Player-prop projections — points, rebounds, assists and more — for the active slate, with Finals context preserved.
Moneyline only (V1). Win probabilities vs the market price. Suggested cards are model-probability only — no market odds, so no paper payout is shown. No method/distance/round props yet.
Why some picks aren't suggested
The model agrees with the market — not enough disagreement to suggest a card. Shown as a projection view.
A player prop needs the confirmed starting lineup before it's card-eligible.
The current odds provider doesn't offer this market for this event yet.
Early-tournament or thin data — confidence is capped until more games are graded.
Methodology, briefly — updated from settled results (June 12)
Ensemble model (market prior + team strength + form), 90-minute regulation only — a draw is a real outcome. Bank Builder legs now require BOTH model and market support; the model-disfavored plus-money side lost on June 11 and is downweighted.
Player props settled nightly against official box scores (8,800+ decisive leans). Hits Overs are the strongest settled market; total-bases and strikeout Overs under-delivered and are excluded from suggested cards, as are outsized model-vs-market edges.
Player props settled against official box scores (3,100+ decisive). REB/PRA were the strongest recent markets — the settled Finals card hit both legs. Season-dependent.
One card per ladder step, full-bankroll stake, official-source settlement, and seven hard gates (real odds, model + market support, low correlation, clear settlement rules, target-fit, no lineup-pending props). No card that clears = no card published.
Glossary
Our model's estimate that an outcome happens, 0–100%.
The same chance baked into the sportsbook price, margin removed.
Model probability minus market probability. Positive = the model likes it more than the price.
−150 = risk 150 to win 100; +130 = risk 100 to win 130.
Several picks combined into one card — all must hit; the odds multiply.
A single pick inside a parlay card.
A player prop shown before the starting lineup is confirmed — labeled until lineups post.
A pick the model rates but the sportsbook doesn't price — shown without a paper payout (e.g. some UFC cards).
A projection the model has, but that hasn't cleared our bar to be a suggested card yet.
GameTime Picks is an educational analytics project. Nothing here is betting advice or a recommendation to wager. Every “stake” and “payout” is hypothetical paper, tracked honestly — wins and losses both. For the full model write-up see Methodology; for our stance see Responsible use.