Game Value — Player board

Does your rating of a player tell us more about what happens while he is on the pitch than his own on-pitch goal difference already does?

That is the whole claim a player rating makes: that it separates a player's contribution from the crude fact of what happened around him. It is what this board measures, and nothing else.

A player rating is the most widely shipped football analytics product there is — live-score apps, media outlets and scouting platforms publish one number per player per match to millions of people every week — and there is almost no public evidence about which of them is any good. Any player-rating product can enter this board, with or without a game value model behind it.

The player board is open. The appearance list is published, ratings are accepted, and the scoring run is weekly. The protocol was published before any score existed, so that it could not be changed to suit a result, and it was rehearsed over three seasons of the five top leagues before anyone was asked for anything. Onboarding is where to start.

The player board in 3:14: the protocol, and one match segment by segment. Figures as of week 39, 29 September 2026.

Three segments of the same match

The obvious test compares a team's results with a player and without him. Across whole matches that compares different matches — different opponents, different venues, and a squad that changed for the same reasons the player is missing.

So each match is cut into three segments, and each is scored as one comparison between the two sides:

Segment	Window
1	kick-off → half-time
2	half-time → 70'
3	70' → full time

A player withdrawn on 68 minutes gives a with-him and a without-him observation inside the same match, against the same opponent, on the same afternoon. Everything that makes two matches hard to compare is held fixed. The boundaries sit where lineups actually change: between one segment and the next, the players on the pitch change in about seven segments in ten.

A player is on the pitch for a segment when he is present for more than half of it, read from the timed match events — the starting eleven, every substitution and every sending-off. A side reduced to ten is scored with ten: discarding matches with a red card would discard the matches where who is on the pitch matters most.

What is scored

The signal is the average rating of the players on the pitch, each rating taken from that player's appearances before this match, weighted by the minutes he played in them. The signal is the difference between the two sides.

That is a hybrid of two times, and deliberately so: who is on the pitch comes from this segment, what they are worth comes from before this match. Rate the players on this match itself and the test becomes circular — a rating given after the final whistle already knows the goals. Fix the eleven at kick-off instead and a substitution changes nothing: all three segments of a match would carry the same number, and the board would lose its closest thing to an experiment — the same team, against the same opponent, on the same afternoon, with one player swapped.

The outcome is the goal difference during that segment.

The baseline is naive plus-minus: each player's own on-pitch goal difference per segment so far, averaged over the players on the pitch exactly as the ratings are. It is the demanding choice, for three reasons:

It neutralises the outcome mimic. A rating that quietly rewards whoever scored tracks plus-minus almost by construction, and scores zero against it.
It absorbs team strength. Good players play for good teams, so a signal built from the eleven on the pitch mostly says which team is which. Nobody wins here by knowing that Bayern are better than Heidenheim.
It is the honest competitor. Plus-minus is what the lineup sheet and the scoreline give for free. A rating that does not beat it is not selling information.

A player with no prior segment this season takes the figure of his club's players in the same position, not the league average — a newcomer at a strong club is not the same bet as one at a weak club.

How hard the bar is

A second reference is published beside the baseline: each segment priced by the two teams' records alone, blind to who is on the pitch. It was expected to sit well below the baseline.

It does not, and that is the most important thing this page has to say. Over the rehearsed seasons the lineup-blind floor landed about 0.004 below plus-minus. Knowing who is on the pitch is worth very little over knowing which two teams are playing: nearly everything the baseline knows is team strength, and a segment's goals barely respond to personnel.

Three things follow:

The bar is honest but nearly saturated. A participant is asked to add something on top of a quantity that is itself almost entirely team strength.
A flat score is not proof of a worthless product. It may equally be a property of football: one segment of one match is very little evidence about an individual.
It is why a second question is published beside this one, judged by somebody other than the Arena — below.

The floor is published on the board so that this can be seen rather than taken on trust. A row below it has no player signal at all.

Comparing like with like

Substitutions are decided by the scoreline: attackers on when chasing, defenders on when protecting a lead. Left alone, being on the pitch late in a match would measure when a player tends to come on rather than what he contributes.

So segments are compared only with segments in the same situation — the same segment of the match, and the same score at its start. A player introduced at 70' with his side two down is measured against other segments that also began two down. The scoring page lists the eleven groups this makes, and what it is worth.

Reading the score

The statistic is Somers' D, as on the team board: of the pairs of segments where one genuinely went better than the other, the net share the ratings put in the right order. The score is the participant's D minus plus-minus's on the identical segments, so zero means adding nothing to what each player's own goal difference already says, and an improvement of +0.02 means the same thing here as on the team board.

The scale does not matter. Ratings arrive out of 10, out of 100, or as z-scores; the score depends only on order, so nothing is rescaled.

Every score carries an interval, and it is the interval that carries the reading. A full season of five competitions resolves to about ±0.015, so most first-season rows will honestly read level with plus-minus; two participants are compared by differencing them on the same resampled matches, never by whether their intervals overlap.

A second question: does the coach pick who you rate?

Published beside the score, on its own ranking:

Of two players at the same club, in the same broad role, already playing about as much as each other — did the one you rated higher get more of the next month's minutes?

This is agreement with the people who pick the team, and it is named that way. It is not a measure of truth. A coach sees training, fitness, tactics and a calendar of cup ties this board cannot see; he also watched the same match the vendor watched, so part of any agreement is common observation.

The bar is the player's own recent minutes, for the same reason the score's bar is his own plus-minus: regulars stay regulars, and a column with no bar would pay any rating that knows who is already in the team. Holding fixed how much he was already playing turns the question from do you know the pecking order into do you know which way it is about to move.

It resolves several times coarser than the score, rests on far fewer comparisons, and it is not the score in different clothes: a signal built from realised goal difference does worse here than a player's own minutes, because coaches do not select on goal difference. A product can be strong on one of these and weak on the other.

The two are never blended into one number. A weighting between the goals followed your players and the coach agreed with you would be the Arena inventing the most important figure on the page.

Taking part

A participant sends one rating per player per appearance — not one per segment — and the Arena decides who was on the pitch for each segment. Ratings are due a full day after a round's last match, freeze at that deadline, and count only toward matches kicking off after it.

You choose which competitions you enter, and are scored only on those. Inside one you rate every appearance you can: picking appearances is picking a sample, and the players a rating system finds hardest to judge are exactly the ones it would have most reason to leave out.
Goalkeepers are included. A keeper's rating is as much of a product claim as an outfielder's, and he decides goals.
A segment counts for you when you have rated at least 9 of the 11 on the pitch on both sides. A mean over a partial eleven is a mean over a selected eleven.
A missing rating is missing, never zero. The share of players you rated is published beside your score.

Onboarding takes you from registering to a first score; the delivery contract is the reference for every call.

What this does not claim

It does not measure a rating against what a match report said, or against who was named man of the match — neither has an answerable form.

It does not bound what a rating could achieve. A rating that captures something about a particular stretch of a particular match — form, a matchup, a role on the day — is not bounded by what a player's durable goal difference is worth, which is why the board publishes no ceiling.

And it is independent of the other two boards. A participant may enter any of them, and none checks a submission against another.