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

Savic

CBMontenegro · Trabzonspor

№ 107010Emerging €431k −0.08

Player dossierSüper Lig

StefanSavic

CBCentre-BackDefender

Club
Trabzonspor
League
Süper Lig
Nationality
Montenegro
Age
35
Height
187 cm
Foot
Right
Valued
21 May 2026

Reading the valuation

The market values Savic at €400k. Model A, which never saw Savic during training, estimates €431k: the market value is 7% below that estimate.

That is a factor of ×1.08. 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 €301k, 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.

▼ −0.08A €431k▲ +0.28B €301k
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
38
Minutes
2,898
Goals
1
Assists
1
Started
34/38
Min / app
76
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 Savic…

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 €400k

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €400kModel A €431k

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 2,065 defenders

Stefan Savic's percentiles among defenders: Goals per 90 49th, Assists per 90 45th, Minutes, two years 51st, Starts 68th, Minutes, last 365 days 53rd, European club minutes 72nd49thGoals45thAssists51stMinutes68thStarts53rdRecent72ndEurope

Dashed ring: the defender median (50th percentile)

European club minutes

Share of minutes played in UEFA club competitions.

10% this player0% defender median72nd 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
€100k
Oct 2009
Peak
€40M
May 2018
Model target
€400k
May 2026
Valuations
47
5 club changes
May 2026€400kTrabzonsporValuation the model is trained to reproduce

May 2026: €400k, Trabzonspor. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2009-10-15€100kFK BSK Borca
2010-05-05€450kFK BSK Borca
2010-11-16€1.5MFK Partizan Belgrade
2011-01-10€2MFK Partizan Belgrade
2011-05-01€3.5MFK Partizan Belgrade
2011-06-21€6MFK Partizan Belgrade
2012-02-06€8.5MManchester City
2012-06-24€8MManchester City
2013-01-15€10MACF Fiorentina
2013-06-19€10MACF Fiorentina
2014-01-07€10.5MACF Fiorentina
2014-07-01€13MACF Fiorentina
2015-01-07€14MACF Fiorentina
2015-07-01€15MACF Fiorentina
2015-11-22€12MAtlético de Madrid
2016-02-22€12MAtlético de Madrid
2016-07-15€20MAtlético de Madrid
2016-10-27€25MAtlético de Madrid
2017-01-24€28MAtlético de Madrid
2017-03-29€30MAtlético de Madrid
2017-06-05€30MAtlético de Madrid
2018-01-01€30MAtlético de Madrid
2018-03-22€35MAtlético de Madrid
2018-05-30€40MAtlético de Madrid
2018-12-21€40MAtlético de Madrid
2019-06-11€35MAtlético de Madrid
2019-12-20€32MAtlético de Madrid
2020-04-08€25.5MAtlético de Madrid
2020-10-08€20MAtlético de Madrid
2021-01-05€25MAtlético de Madrid
2021-06-10€25MAtlético de Madrid
2021-12-30€20MAtlético de Madrid
2022-06-03€16MAtlético de Madrid
2022-09-23€14MAtlético de Madrid
2022-11-07€9MAtlético de Madrid
2023-03-23€7.5MAtlético de Madrid
2023-06-13€6MAtlético de Madrid
2023-12-22€5MAtlético de Madrid
2024-03-21€3MAtlético de Madrid
2024-06-07€2.5MAtlético de Madrid
2024-10-04€2MTrabzonspor
2024-12-23€1.3MTrabzonspor
2025-03-20€1.1MTrabzonspor
2025-06-18€900kTrabzonspor
2025-12-17€700kTrabzonspor
2026-03-05€500kTrabzonspor
2026-05-21€400kTrabzonspor

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
−0.075

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 →

Süper Lig428 players · median €1.2M

Valued above 15% of the 428 Süper Lig players.

€50k€300k€2M€15M€400kSee them in the Explorer →

Defenders, all leagues2,065 players · median €2M

Valued above 14% of the 2,065 defenders.

€20k€200k€2M€20M€400kSee them in the Explorer →

Where Savic 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).