Quant · Predictive intelligence

See football in a new way

Every regular outfield player in 14 divisions, rated 1 to 20 against his position in his own division. Every club too. Like a game you already know, with real numbers: next games, injury news where our feed has it, which numbers really last. And our forecasts, scored in public.

Team cards 264 clubs Forecasts, scored Quant Lab
Team cards

Top of the table, right now

The leader of every division we cover. Tap a club for its formations, the XI that last played each one, ratings, squad and who is out.

Scroll sideways for all 14 divisions.
Built for everyone

Who it's for

Like a game you know, with real numbers

Every outfield player with 900+ league minutes last season, rated 1 to 20 against his own position in his own division. Tap any rating for the real number behind it.

  • 3,970 players and 264 clubs
  • The next game for everyone. Injury and suspension news in the 7 divisions our feed covers
  • Club formations on a pitch you can swipe
  • Betting: every bet the model makes is logged before kick-off and settled after, 157 of them so far at +9.5% ROI. Win or lose, they are all in the ledger
Open player cardsTeam cardsThe betting ledger

Which of your numbers will last?

Some stats carry from one season to the next. Some are mostly luck. We measured which, so you know what to work on and what to ignore.

  • Volume and behaviour carry over
  • Shot conversion barely does
  • See where you rank in your position, if you played 900+ league minutes in one of our 14 divisions
Which stats lastHow much finishing is real

What type of player to look at

Sort every player by any rating, within his position and division. Then check what a big season is actually worth before you pay for it.

  • Filter by division and position, sort by any rating
  • What a league move does to a player's shots
  • Honest tests of our own picks, including the ones that failed
Find playersLeague moves

Risk you can see

Injury risk on player cards where we have the history, from a model tested on a season it never saw.

  • Last season's injuries predict next season's
  • Age barely does, and neither does workload
What predicts injuriesSee injury risk
The crystal ball that keeps score

We predict. Then we mark our own homework.

An 80% range should catch the real outcome eight times in ten. Here is how ours did, scored only on what was known at the time of each forecast. And where we were wrong, we said so.

78%

Our 80% range for a club's final Premier League position, built from betting prices ten games in, held 78% of the time over four past seasons (2022/23 to 2025/26).

Where will they finish →
82%

How much of a striker's finishing is real: between a fifth and a third, in all 14 leagues. Our 80% ranges held 82% of outcomes.

Read it →
We were wrong

Our transfer picks looked far better than the clubs' own. Then we let each player go to only one club, and the advantage did not hold. We published that too.

For the same money →
Quant Lab

Research, in plain English

What the numbers say about football, tested before we publish it.

Arsenal's left wing: what's missing, and three January targetsArsenal's left matched the top six last season. Both men who played there have gone and Tzolis is injured. Three of 120 left wingers pass our filters and project to replace what left. One costs less than Tzolis did.Read →Where will they finish? We scored ourselvesWe built league forecasts from closing betting prices and scored them on four seasons, then forecast divisions up to three seasons ahead and scored those on twelve. The ranges hold. The weak spot is clubs we call fairly safe.Read →What actually predicts a footballer's injuries5,133 player-seasons in 7 leagues. Last season's injuries predict next season's. Age barely does, and neither does workload. Tested on a season the model never saw.Read →How much of a striker's finishing is realBetween a fifth and a third, in all 14 leagues we measured. Our 80% ranges held 82% of outcomes. And 61 calls on this season, frozen before most of it is played.Read →For the same money, would we have bought better?We rebuilt 120 clubs' summer 2024 windows with their own budgets. Our picks looked far better until each player could go to only one club. Then they weren't.Read →Which football stats actually mean anythingWe measured how much of the gap between players on each metric survives to the next season. Volume persists. Efficiency doesn't. 657 Premier League season-pairs, method open.Read →What a league move does to a player's shots1,262 moves across 14 divisions. Stepping up costs shots, moving between top leagues makes no clear difference. And where our ranges failed the test, we say so.Read →What a season of 23 assists is actually worthSplitting one player's season into the half that describes him and the half that describes his teammates. Christos Tzolis, live, with a closed case to check the method against.Read →The half of a striker's season worth paying forFinishing barely persists, so the obvious move is to stop looking at goals and look at shots instead. We tested that and it's wrong. 147 Premier League attacker season-pairs.Read →
All research
The proving ground

We also bet, in public

Sport is the harshest scoring environment we could find. Every forecast gets a price attached, a closing line to measure against, and a result inside ninety minutes.

So we bet. Not because tipping is the business, but because a bet is a forecast with money and a timestamp on it. This is a working track record, not a finished one: 157 bets is suggestive, 500+ is what significance looks like.
157
audited bets
50.3%
strike rate
+9.5%
ROI on stakes
12 March 2026
record starts

Every bet logged. Every result settled. The numbers are not 96%. They are real.

See the track recordRead the ledger
What we do
  • Publish single bets above gate, sized to edge
  • Document the reasoning per fire and per sit
  • Re-check at T-45 when lineups land
  • Settle and publish the result, win or lose
  • Publish closing-odds for every bet (CLV currently being re-verified)
What we don’t
  • Accumulator bait or “banker of the day”
  • 96% accuracy claims
  • Celebrity endorsements (real or AI-faked)
  • “The AI does the work” mystique. A model produces numbers, a human decides
  • Tipping. We're not tipsters. We're a multi-predictive intelligence system reading predictive markets
Follow on X · @quantedgesynd