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…

Taison

LWBrazil · PAOK Thessaloniki

№ 76028Emerging €600k −0.88

Player dossierSuper League

Taison

LWLeft WingerAttack

Club
PAOK Thessaloniki
League
Super League
Nationality
Brazil
Age
38
Height
172 cm
Foot
Right
Valued
4 Jun 2026

Reading the valuation

The market values Taison at €250k. Model A, which never saw Taison during training, estimates €600k: the market value is 58% below that estimate.

That is a factor of ×2.40. 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 €1.1M, 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.

▼ −0.88A €600k▼ −1.51B €1.1M
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
80
Minutes
5,402
Goals
13
Assists
10
Started
61/80
Min / app
68
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 Taison…

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 €250k

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €250kModel A €600k

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 1,583 attackers

Taison's percentiles among attackers: Goals per 90 41st, Assists per 90 57th, Minutes, two years 94th, Starts 78th, Minutes, last 365 days 92nd, European club minutes 95th41stGoals57thAssists94thMinutes78thStarts92ndRecent95thEurope

Dashed ring: the attacker median (50th percentile)

European club minutes

Share of minutes played in UEFA club competitions.

31% this player0% attacker median95th percentile

0%peer deciles · median line · this player ●100%

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
€50k
Jun 2008
Peak
€15M
Jan 2013
Model target
€250k
Jun 2026
Valuations
45
4 club changes
Jun 2026€250kPAOK ThessalonikiValuation the model is trained to reproduce

Jun 2026: €250k, PAOK Thessaloniki. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2008-06-29€50kSport Club Internacional
2008-07-14€800kSport Club Internacional
2008-08-06€1MSport Club Internacional
2008-12-12€1.8MSport Club Internacional
2009-05-19€3.5MSport Club Internacional
2009-09-06€2.5MSport Club Internacional
2009-12-08€2MSport Club Internacional
2010-04-14€1.7MSport Club Internacional
2010-06-06€1.2MSport Club Internacional
2010-08-29€3MMetalist Kharkiv
2011-01-02€6MMetalist Kharkiv
2012-01-05€7.5MMetalist Kharkiv
2012-04-10€9MMetalist Kharkiv
2012-08-22€10MMetalist Kharkiv
2012-11-22€12MMetalist Kharkiv
2013-01-22€15MShakhtar Donetsk
2014-06-30€15MShakhtar Donetsk
2014-12-25€15MShakhtar Donetsk
2015-06-07€15MShakhtar Donetsk
2015-12-18€14MShakhtar Donetsk
2016-07-21€13MShakhtar Donetsk
2017-01-03€12MShakhtar Donetsk
2017-06-26€12MShakhtar Donetsk
2018-01-12€11MShakhtar Donetsk
2018-08-06€11MShakhtar Donetsk
2018-12-10€13MShakhtar Donetsk
2019-06-20€12MShakhtar Donetsk
2020-01-08€12MShakhtar Donetsk
2020-04-08€9.5MShakhtar Donetsk
2020-09-04€8MShakhtar Donetsk
2021-01-14€7MShakhtar Donetsk
2021-05-28€7MSport Club Internacional
2021-12-17€5MSport Club Internacional
2022-04-06€4MSport Club Internacional
2022-08-19€2.5MSport Club Internacional
2022-11-14€1.8MSport Club Internacional
2023-02-27€1.5MPAOK Thessaloniki
2023-05-22€1MPAOK Thessaloniki
2023-09-21€600kPAOK Thessaloniki
2023-12-20€600kPAOK Thessaloniki
2024-05-30€500kPAOK Thessaloniki
2024-12-18€450kPAOK Thessaloniki
2025-05-23€300kPAOK Thessaloniki
2025-12-12€275kPAOK Thessaloniki
2026-06-04€250kPAOK Thessaloniki

Audit context group-level, not about this player

Audit group
non-UEFA
Population gap, Model A
+0.093 95% CI +0.063 to +0.124
This player, market vs held-out A
−0.876

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 →

Super League356 players · median €600k

Valued above 15% of the 356 Super League players.

€20k€150k€1M€7.5M€250kSee them in the Explorer →

Attackers, all leagues1,583 players · median €2.5M

Valued above 6% of the 1,583 attackers.

€20k€300k€5M€75M€250kSee them in the Explorer →

Where Taison 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).