Duk

LWCape Verde · CD Leganés

№ 535959Established €3.2M −0.25

Player dossierLaLiga

Duk

LWLeft WingerAttack

Club: CD Leganés
League: LaLiga
Nationality: Cape Verde
Age: 25
Height: 182 cm
Foot: Right
Valued: 30 Dec 2025

Reading the valuation

The market values Duk at €2.5M. Model A, which never saw Duk during training, estimates €3.2M: the market value is 22% below that estimate.

That is a factor of ×1.29. 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 €1.3M, 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.

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: 47
Minutes: 1,921
Goals: 4
Assists: 3
Started: 16/47
Min / app: 41
Cards: 10Y 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 Duk…

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 €2.5M

Checking API

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

Dashed ring: the attacker median (50th percentile)

Assists per 90

Club assists per 90 minutes in the same window.

0.14 this player0.15 attacker median48th percentile

0.00peer deciles · median line · this player ●0.73

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: €250k; Nov 2020
Peak: €2.5M; Dec 2025
Model target: €2.5M; Dec 2025
Valuations: 14; 2 club changes

Dec 2025€2.5MCD LeganésValuation the model is trained to reproduce

Dec 2025: €2.5M, CD Leganés. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table

Date	Market value	Club
2020-11-02	€250k	SL Benfica B
2021-06-29	€250k	SL Benfica B
2022-04-01	€175k	SL Benfica B
2022-06-27	€200k	SL Benfica B
2022-12-13	€500k	Aberdeen FC
2023-03-22	€1M	Aberdeen FC
2023-06-26	€1.8M	Aberdeen FC
2023-12-05	€1.8M	Aberdeen FC
2024-03-20	€1.5M	Aberdeen FC
2024-05-30	€1.5M	Aberdeen FC
2024-12-03	€1.2M	Aberdeen FC
2025-06-09	€1M	CD Leganés
2025-10-16	€1.5M	CD Leganés
2025-12-30	€2.5M	CD Leganés

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: −0.254

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 →

LaLiga509 players · median €4M

Valued above 34% of the 509 LaLiga players.

See them in the Explorer →

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

Valued above 48% of the 1,583 attackers.

See them in the Explorer →

Where Duk appears

TerminalLaLiga in the Player Explorer
TerminalLaLiga on the League Landscape

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).