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 David de Gea

David de

Gea

GKSpain · ACF Fiorentina

№ 59377Established €1.7M +0.73

Close-up

Image: FootyLogos

Player dossierSerie A

David deGea

GKGoalkeeperGoalkeeper

Club
ACF Fiorentina
League
Serie A
Nationality
Spain
Age
35
Height
192 cm
Foot
Right
Valued
29 May 2026

Reading the valuation

The market values Gea at €3.5M. Model A, which never saw Gea during training, estimates €1.7M: the market value is 107% above that estimate.

That is a factor of ×2.07. Model A's typical held-out miss is ×1.50 either way, so this gap is larger than its usual error.

Without league and club, Model B estimates €1.5M, 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.

▲ +0.73A €1.7M▲ +0.86B €1.5M
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
76
Minutes
6,870
Started
76/76
Min / app
90
Cards
1Y 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 Gea…

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 €3.5M

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €3.5MModel A €1.7M

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 485 goalkeepers

David de Gea's percentiles among goalkeepers: Minutes, two years 92nd, Starts 62nd, Minutes, last 365 days 91st, European club minutes 68th92ndMinutes62ndStarts91stRecent68thEurope

Dashed ring: the goalkeeper median (50th percentile)

Minutes, two years

Total club minutes in the two-year window: how much the player was used.

6,870 this player2,790 goalkeeper median92nd percentile

450peer deciles · median line · this player ●9,210

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
€100k
Nov 2007
Peak
€70M
May 2018
Model target
€3.5M
May 2026
Valuations
45
4 club changes
May 2026€3.5MACF FiorentinaValuation the model is trained to reproduce

May 2026: €3.5M, ACF Fiorentina. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2007-11-23€100kAtlético Madrid U19
2009-08-06€500kAtlético de Madrid
2009-12-03€800kAtlético de Madrid
2010-01-29€3MAtlético de Madrid
2010-04-12€7MAtlético de Madrid
2010-08-27€12MAtlético de Madrid
2011-02-04€12MAtlético de Madrid
2011-08-08€18MManchester United
2012-02-06€16MManchester United
2012-06-24€17.5MManchester United
2013-01-28€17MManchester United
2013-07-02€17MManchester United
2014-01-15€17MManchester United
2014-08-12€18MManchester United
2015-02-12€25MManchester United
2015-07-01€30MManchester United
2016-02-09€35MManchester United
2016-06-01€40MManchester United
2016-08-01€40MManchester United
2017-02-20€40MManchester United
2017-06-28€40MManchester United
2018-01-02€50MManchester United
2018-03-23€60MManchester United
2018-05-28€70MManchester United
2018-12-19€70MManchester United
2019-06-13€65MManchester United
2019-12-10€60MManchester United
2020-03-09€50MManchester United
2020-04-08€40MManchester United
2020-10-13€35MManchester United
2020-12-17€25MManchester United
2021-03-18€22MManchester United
2021-05-31€18MManchester United
2021-12-23€18MManchester United
2022-03-29€15MManchester United
2022-06-15€15MManchester United
2022-11-03€15MManchester United
2023-06-20€13MManchester United
2023-10-25€8MWithout Club
2024-03-29€5MWithout Club
2024-10-18€5MACF Fiorentina
2024-12-18€5MACF Fiorentina
2025-06-17€5MACF Fiorentina
2025-12-23€3.5MACF Fiorentina
2026-05-29€3.5MACF Fiorentina

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
+0.726

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 →

Serie A507 players · median €5.5M

Valued above 34% of the 507 Serie A players.

€100k€750k€5M€30M€3.5MSee them in the Explorer →

Goalkeepers, all leagues485 players · median €1M

Valued above 72% of the 485 goalkeepers.

€20k€200k€2M€20M€3.5MSee them in the Explorer →

Where Gea 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).