Best bets

Every team gets an offence and a defence rating in points: what it scores and concedes beyond what an average side would against the same opponents. Those give an expected margin and an expected total, and every market is read off those two numbers and the spread of real results around them.

There is no quarterback adjustment in these ratings. It is the largest single swing in the sport, and a team rating fitted over sixteen games cannot be told that four of them were a backup — that needs a player-level adjustment, and half of one would be worse than saying so. A fixture whose listed starter is on the injury report is flagged by name; the club’s depth chart is on its own page.

It is fitted on points scored, with a match halving in weight every 140 days. Both of those were chosen by the backtest rather than by preference: expected points added lost to plain points here, because we hold each team’s EPA total for a game rather than its rate per play, and a game total is close to a restatement of the score.

Margin, average miss

9.98 pts

Always-home would miss

10.97 pts

Winner called right

63.0%

Calibration error

2.0%

Measured over 1,168 NFL fixtures it had not seen, across 2021–2025. The ratings were refitted at the start of every round from the matches played before it and nothing after, which is the situation you are in on a Friday.

What the edge is, and what it is not

A worked example, kept fixed so the arithmetic can be followed rather than re-checked against a board that moves every week. Crystal Palace to score at least once, at 1.53. The model makes it 73.3% and the books’ own prices make it 64.2%; blended, it is about 67%. That gives an edge of +2.8%, which means: stake one unit on bets like this over and over, and you finish 0.028 units ahead per unit staked, on average.

It is not 53%. A winning bet at 1.53 returns 1.53 — a profit of 0.53 — but it only wins about two times in three, and the third time the whole unit is gone. 0.67 × 0.53 − 0.33 × 1 is where the 2.8% comes from. The edge is the number that survives the losses; the price is the number that does not.

Why the biggest edge is not always the pick

A board is ranked on the stake, which is the Kelly fraction — the edge divided by what the bet stands to lose — taken at a quarter. At the same edge a shorter price is the better bet, because the same money is at risk for far less of the time, and an edge on its own cannot see that. On Aston Villa against Arsenal the outright at 7.00 carries almost three times the edge of Villa-or-the-draw at 2.60, and the double chance is still the better bet: 5.8% of a bankroll against 4.6%.

Which is also why a bet that won is not, on its own, evidence the board was wrong to name a different one. Every row here is priced to be taken many times; one result decides nothing about any of them. The place that question gets answered is the record, over as many bets as there have been.

What confidence is made of

• Sample. How much football is behind the weaker of the two ratings. A promoted club in August has almost none, and the score says so.
• Corroboration. How many books quote the bet, and how far the best price sits above the rest. A standout and a stale quote look identical from here.
• Calibration. How the model behaved at this probability in the backtest - not on average. A model can be excellent overall and over-confident in one band, and a bettor bets the band, not the average.
• Agreement. How far the model has strayed from the market’s own devigged view. A model claiming a bet is twice as likely as the whole market thinks has almost certainly missed something - a suspension, a rested squad, a goalkeeper - and this is a brake, not an accelerator.

Why there are no player props here

Because they are measured against something else entirely, and putting the two in one ranked list would imply a comparison neither number supports. A team market has a complete set of outcomes, so the bookmakers’ own margin can be removed and the model checked against what the market really thinks. Australian books quote a player prop one way — there is no Under to devig against — so the only honest yardstick is the player’s own record, which is a fact about the past rather than a claim about the match.

They are on the value board, ranked on that record, in their own table for the same reason. Bringing them here needs one confidence scale that spans a model probability and a hit rate, and that does not exist yet.

What has not been proved

The model is measured against results, and it is good at them. It has never been measured against a closing price, and cannot be: this database has only ever stored the current round’s odds, so there are no historical lines to test against and there never will be for the seasons already gone. Until that record exists, the model is given at most equal weight with the market rather than more - the edges you see are already blended on that basis.

Every run stores its probability beside the price it could have been struck at, and the record grades all of it against what happened. It is far too short to draw anything from yet, and it says so.

Model nfl-points-1 · fitted 8 Sept 2026, 4:48 pm (Sydney) · nothing after that instant was read.