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…

Dirk

Proper

DMNetherlands · NEC Nijmegen

№ 485587Emerging €2.9M −0.65

Player dossierEredivisie

DirkProper

DMDefensive MidfieldMidfield

Club
NEC Nijmegen
League
Eredivisie
Nationality
Netherlands
Age
24
Height
167 cm
Foot
Right
Valued
28 May 2026

Reading the valuation

The market values Proper at €1.5M. Model A, which never saw Proper during training, estimates €2.9M: the market value is 48% below that estimate.

That is a factor of ×1.92. 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 €1.6M, closer to the market here, although it is usually further off (typical miss ×2.07).

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

▼ −0.65A €2.9M▼ −0.04B €1.6M
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
52
Minutes
3,529
Goals
3
Assists
2
Started
37/52
Min / app
68
Cards
5Y 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 Proper…

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 €1.5M

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €1.5MModel A €2.9M

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

Dirk Proper's percentiles among midfielders: Goals per 90 47th, Assists per 90 29th, Minutes, two years 66th, Starts 54th, Minutes, last 365 days 44th, European club minutes 30th47thGoals29thAssists66thMinutes54thStarts44thRecent30thEurope

Dashed ring: the midfielder median (50th percentile)

Minutes, two years

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

3,529 this player2,607 midfielder median66th percentile

451peer deciles · median line · this player ●9,624

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
€400k
Jan 2020
Peak
€6M
May 2024
Model target
€1.5M
May 2026
Valuations
21
0 club changes
May 2026€1.5MNEC NijmegenValuation the model is trained to reproduce

May 2026: €1.5M, NEC Nijmegen. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2020-01-17€400kNEC Nijmegen
2020-04-08€350kNEC Nijmegen
2020-06-29€550kNEC Nijmegen
2020-10-24€625kNEC Nijmegen
2020-12-31€650kNEC Nijmegen
2021-10-04€800kNEC Nijmegen
2022-01-05€900kNEC Nijmegen
2022-06-08€900kNEC Nijmegen
2022-11-11€900kNEC Nijmegen
2023-03-17€2MNEC Nijmegen
2023-06-23€2MNEC Nijmegen
2023-10-17€3MNEC Nijmegen
2023-12-15€3MNEC Nijmegen
2024-03-18€5MNEC Nijmegen
2024-05-31€6MNEC Nijmegen
2024-12-17€4.5MNEC Nijmegen
2025-03-28€4MNEC Nijmegen
2025-05-28€3MNEC Nijmegen
2025-12-02€2.3MNEC Nijmegen
2026-03-11€2MNEC Nijmegen
2026-05-28€1.5MNEC Nijmegen

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
−0.654

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 →

Eredivisie425 players · median €1M

Valued above 54% of the 425 Eredivisie players.

€75k€500k€3M€20M€1.5MSee them in the Explorer →

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

Valued above 39% of the 1,687 midfielders.

€20k€200k€2M€20M€1.5MSee them in the Explorer →

Where Proper 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).