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…

Stuart

Armstrong

CMScotland · Aberdeen FC

№ 130765Emerging €74k +0.99

Player dossierPremiership

StuartArmstrong

CMCentral MidfieldMidfield

Club
Aberdeen FC
League
Premiership
Nationality
Scotland
Age
34
Height
183 cm
Foot
Right
Valued
20 May 2026

Reading the valuation

The market values Armstrong at €200k. Model A, which never saw Armstrong during training, estimates €74k: the market value is 170% above that estimate.

That is a factor of ×2.70. 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 €216k, 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.

▲ +0.99A €74k▼ −0.08B €216k
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
27
Minutes
1,974
Goals
1
Assists
4
Started
23/27
Min / app
73
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 Armstrong…

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 €200k

Checking API
EmergingEstablishedEliteWorld Class€2M€10M€30M€100k€1M€100MMarket €200kModel A €74k

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

Stuart Armstrong's percentiles among midfielders: Goals per 90 32nd, Assists per 90 79th, Minutes, two years 35th, Starts 79th, Minutes, last 365 days 64th, European club minutes 30th32ndGoals79thAssists35thMinutes79thStarts64thRecent30thEurope

Dashed ring: the midfielder median (50th percentile)

Assists per 90

Club assists per 90 minutes in the same window.

0.18 this player0.09 midfielder median79th percentile

0.00peer deciles · median line · this player ●0.74

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
Jul 2011
Peak
€8M
Dec 2018
Model target
€200k
May 2026
Valuations
32
5 club changes
May 2026€200kAberdeen FCValuation the model is trained to reproduce

May 2026: €200k, Aberdeen FC. Dotted lines mark the €2M, €10M and €30M tier boundaries.

Show as a table
DateMarket valueClub
2011-07-11€50kDundee United FC
2012-02-02€250kDundee United FC
2012-07-23€250kDundee United FC
2013-02-14€450kDundee United FC
2013-10-08€500kDundee United FC
2014-02-13€550kDundee United FC
2014-10-09€500kDundee United FC
2015-01-10€600kDundee United FC
2015-11-30€1.3MCeltic FC
2017-02-14€1.5MCeltic FC
2018-03-04€2MCeltic FC
2018-08-13€7MSouthampton FC
2018-12-19€8MSouthampton FC
2019-06-13€8MSouthampton FC
2019-12-10€8MSouthampton FC
2020-04-08€6.5MSouthampton FC
2020-10-13€6.5MSouthampton FC
2021-03-18€6.5MSouthampton FC
2021-05-28€8MSouthampton FC
2021-12-23€6MSouthampton FC
2022-06-15€6MSouthampton FC
2022-11-03€6MSouthampton FC
2023-06-20€4.5MSouthampton FC
2023-10-27€3MSouthampton FC
2023-12-21€2MSouthampton FC
2024-05-24€2MSouthampton FC
2024-12-12€1.5MVancouver Whitecaps FC
2025-05-27€800kSheffield Wednesday
2025-10-08€700kAberdeen FC
2025-12-10€600kAberdeen FC
2026-03-05€400kAberdeen FC
2026-05-20€200kAberdeen FC

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
+0.993

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 →

Premiership311 players · median €400k

Valued above 26% of the 311 Premiership players.

€20k€150k€1M€7.5M€200kSee them in the Explorer →

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

Valued above 3% of the 1,687 midfielders.

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

Where Armstrong 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).