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…

Stefan

Schwab

CMAustria · Holstein Kiel

№ 79612Emerging €628k −0.74

Player dossierBundesliga

StefanSchwab

CMCentral MidfieldMidfield

Club
Holstein Kiel
League
Bundesliga
Nationality
Austria
Age
35
Height
183 cm
Foot
Left
Valued
16 Dec 2025

Reading the valuation

The market values Schwab at €300k. Model A, which never saw Schwab during training, estimates €628k: the market value is 52% below that estimate.

That is a factor of ×2.09. 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 €407k, 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.

▼ −0.74A €628k▼ −0.31B €407k
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
55
Minutes
2,872
Goals
8
Assists
3
Started
31/55
Min / app
52
Cards
6Y 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 Schwab…

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 €300k

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €300kModel A €628k

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

Stefan Schwab's percentiles among midfielders: Goals per 90 89th, Assists per 90 50th, Minutes, two years 55th, Starts 29th, Minutes, last 365 days 20th, European club minutes 94th89thGoals50thAssists55thMinutes29thStarts20thRecent94thEurope

Dashed ring: the midfielder median (50th percentile)

European club minutes

Share of minutes played in UEFA club competitions.

27% this player0% midfielder median94th percentile

0%peer deciles · median line · this player ●85%

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
€75k
Mar 2009
Peak
€2.5M
Jun 2018
Model target
€300k
Dec 2025
Valuations
42
5 club changes
Dec 2025€300kHolstein KielValuation the model is trained to reproduce

Dec 2025: €300k, Holstein Kiel. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2009-03-16€75kRed Bull Juniors Salzburg (- 2012)
2009-04-16€100kRed Bull Juniors Salzburg (- 2012)
2009-08-11€125kRed Bull Juniors Salzburg (- 2012)
2009-09-23€175kRed Bull Juniors Salzburg (- 2012)
2009-11-09€200kRed Bull Juniors Salzburg (- 2012)
2010-05-29€175kRed Bull Juniors Salzburg (- 2012)
2010-10-01€225kFC Lustenau
2011-04-07€300kFC Admira Wacker Mödling
2011-09-21€450kFC Admira Wacker Mödling
2011-12-30€550kFC Admira Wacker Mödling
2012-05-30€600kFC Admira Wacker Mödling
2012-09-24€550kFC Admira Wacker Mödling
2012-12-19€550kFC Admira Wacker Mödling
2013-06-04€650kFC Admira Wacker Mödling
2013-12-27€800kFC Admira Wacker Mödling
2014-06-20€800kFC Admira Wacker Mödling
2015-01-11€1MRapid Vienna
2015-06-17€1MRapid Vienna
2015-10-02€1.3MRapid Vienna
2015-12-29€1.5MRapid Vienna
2016-06-01€1.5MRapid Vienna
2016-12-22€2MRapid Vienna
2017-06-02€2MRapid Vienna
2018-01-02€2MRapid Vienna
2018-06-14€2.5MRapid Vienna
2018-12-19€2.5MRapid Vienna
2019-06-03€2MRapid Vienna
2019-12-16€2MRapid Vienna
2020-04-08€1.6MRapid Vienna
2020-07-22€1.5MRapid Vienna
2021-02-12€1.8MPAOK Thessaloniki
2021-05-30€2MPAOK Thessaloniki
2021-11-01€2MPAOK Thessaloniki
2022-02-22€1.5MPAOK Thessaloniki
2022-06-09€1.2MPAOK Thessaloniki
2022-11-07€1MPAOK Thessaloniki
2023-05-22€1MPAOK Thessaloniki
2023-12-20€1MPAOK Thessaloniki
2024-05-30€900kPAOK Thessaloniki
2024-12-18€800kPAOK Thessaloniki
2025-05-23€600kPAOK Thessaloniki
2025-12-16€300kHolstein Kiel

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
−0.738

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 →

Bundesliga451 players · median €5M

The joint lowest observed value among 451 Bundesliga players.

€300k€2M€15M€100M€300kSee them in the Explorer →

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

Valued above 7% of the 1,687 midfielders.

€20k€200k€2M€20M€300kSee them in the Explorer →

Where Schwab 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).