FairValue

Checking model

Esc

  • EnvironmentOverviewWhat FairValue measures, what it found, where to go next.
  • EnvironmentTerminalExplore, compare and track players; market, league and model views.
  • EnvironmentStoriesValuations, head-to-heads and research findings, told as stories.
  • TerminalPlayer ExplorerSearch, filter and sort the player export.
  • TerminalComparison StudioTwo to four players on one scale.
  • TerminalWatchlistsNamed collections, kept in this browser.
  • TerminalMarket LandscapeHow observed value is distributed, and where the model drifts.

↑ ↓ to move · Enter to open · Esc to closeLoading player index…

Portrait of James Milner

James

Milner

CMEngland · Brighton & Hove Albion

№ 3333Emerging €530k −0.06

Image: FootyLogos

Player dossierPremier League

JamesMilner

CMCentral MidfieldMidfield

Club
Brighton & Hove Albion
League
Premier League
Nationality
England
Age
40
Height
175 cm
Foot
Right
Valued
3 Jun 2026

Reading the valuation

The market values Milner at €500k. Model A, which never saw Milner during training, estimates €530k: the market value is 6% below that estimate.

That is a factor of ×1.06. Model A's typical held-out miss is ×1.50 either way, so this gap is within its usual error.

Without league and club, Model B estimates €171k, further from the market. Model B is usually further off (typical miss ×2.07): league and club explain much of how the market prices players.

A gap describes the model's arithmetic for this player's inputs, not what the player is worth.

▼ −0.06A €530k▲ +1.07B €171k
Pitch length is a log value scale fitted to this player's figures. ● observed · ◇ Model A · dashed ◇ Model B · each arc is a residual, log(observed) − log(estimate).
Apps
26
Minutes
1,119
Goals
1
Assists
1
Started
12/26
Min / app
43
Cards
3Y 0R

Club matches, two years to the valuation date

The Valuation Journey

What moves Model A

Asking the prediction API to explain Model A for Milner…

SHAP describes the model's arithmetic for this player's inputs, not what causes market value. Model B can be explained only by the live service; Model A also has a published explanation for the research players.

Model A vs Model B against the observed €500k

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €500kModel A €530k

Asking the prediction API…

Held-out estimates come from cross-validation, with this player outside the training data: the honest comparison. Served models were refitted on every player, this one included, so they sit closer to the market. Shaded band: Model A's typical miss (×1.50 either way).

Player traitspercentiles vs 1,687 midfielders

James Milner's percentiles among midfielders: Goals per 90 49th, Assists per 90 44th, Minutes, two years 16th, Starts 17th, Minutes, last 365 days 30th, European club minutes 30th49thGoals44thAssists16thMinutes17thStarts30thRecent30thEurope

Dashed ring: the midfielder median (50th percentile)

Goals per 90

Club goals per 90 minutes played in the two years to the valuation date.

0.08 this player0.08 midfielder median49th percentile

0.00peer deciles · median line · this player ●0.93

No passing, progression or defensive actions exist in the dataset, so no trait claims to measure them.

Valuation history every Transfermarkt valuation on record

First valuation
€7.5M
Oct 2004
Peak
€21M
Jun 2012
Model target
€500k
Jun 2026
Valuations
46
6 club changes
Jun 2026€500kBrighton & Hove AlbionValuation the model is trained to reproduce

Jun 2026: €500k, Brighton & Hove Albion. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2004-10-04€7.5MNewcastle United
2005-02-01€5.5MNewcastle United
2005-09-01€6MAston Villa
2006-04-17€4.7MAston Villa
2007-09-01€8MNewcastle United
2008-01-29€8.8MNewcastle United
2008-09-01€10MAston Villa
2009-02-23€11.5MAston Villa
2009-06-26€13MAston Villa
2010-01-24€17MAston Villa
2010-08-13€20MAston Villa
2011-02-01€20MManchester City
2011-08-08€18MManchester City
2012-02-06€20MManchester City
2012-06-24€21MManchester City
2013-01-28€17MManchester City
2013-07-02€18MManchester City
2014-01-15€15MManchester City
2014-08-12€14MManchester City
2015-02-12€14MManchester City
2015-07-01€14MLiverpool FC
2016-02-09€14MLiverpool FC
2016-06-01€15MLiverpool FC
2016-08-01€15MLiverpool FC
2017-02-20€15MLiverpool FC
2017-06-28€12MLiverpool FC
2018-01-02€12MLiverpool FC
2018-05-28€15MLiverpool FC
2018-12-19€15MLiverpool FC
2019-06-13€15MLiverpool FC
2019-12-10€12MLiverpool FC
2020-03-09€8MLiverpool FC
2020-04-08€6.5MLiverpool FC
2020-10-13€5MLiverpool FC
2021-03-18€3MLiverpool FC
2021-06-08€3MLiverpool FC
2021-12-23€2MLiverpool FC
2022-06-15€2MLiverpool FC
2022-11-03€2MLiverpool FC
2023-06-20€1.5MLiverpool FC
2023-12-19€1MBrighton & Hove Albion
2024-05-27€1MBrighton & Hove Albion
2024-12-16€1MBrighton & Hove Albion
2025-05-30€1MBrighton & Hove Albion
2025-12-09€750kBrighton & Hove Albion
2026-06-03€500kBrighton & Hove Albion

Audit context group-level, not about this player

Audit group
UEFA
Population gap, Model A
+0.093 95% CI +0.063 to +0.124
This player, market vs held-out A
−0.059

The group comes from first-listed citizenship and is never a model input. Across the population, non-UEFA players' market values sit about 10% above Model A's held-out estimates, relative to UEFA players in the same leagues. One player's residual says nothing about that pattern (typical miss ×1.50), and none of it is evidence of discrimination: the target may itself be biased. Open the Fairness Audit

In context observed value among comparable players in this build

All players in the Terminal →

Premier League555 players · median €18M

Valued above 3% of the 555 Premier League players.

€150k€1M€7.5M€50M€500kSee them in the Explorer →

Midfielders, all leagues1,687 players · median €2M

Valued above 16% of the 1,687 midfielders.

€20k€200k€2M€20M€500kSee them in the Explorer →

Where Milner appears

Watchlists and the comparison tray are kept in this browser only.

Near this valuation closest observed values: same league, then same position

Counts and ranks of observed Transfermarkt values only; model errors are never ranked here. Full player export: Every player in the modelling population (D-011).