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…

CM · Central Midfield

Khéphren

Thuram

Serie A · 25 · €38M observed

DM · Defensive Midfield

Idrissa

Gueye

Premier League · 36 · €500k observed

Head-to-Head story

Thuram v Gueye

Central Midfield in Serie A at €38M, defensive midfield in Premier League at €500k. The model sits above the market for both, by different margins.

Built from Published SHAP output for the served Model A (reports/explainability); the player was in its training data.Portraits: image credits

01

On one scale

Thuram€38MA €41.4M
Gueye€500kA €796k

observed value Model A (served, in-sample) · dashed lines: €2M, €10M, €30M tier boundaries · log scale

02

The tale of the tape

  1. 25Age36
  2. 96Appearances65
  3. 6,468Minutes, two years5,369
  4. 3,394Minutes, last 365 days2,102
  5. 78%Share of games started95%
  6. 0.13Goals per 900.03
  7. 0.18Assists per 900.10
  8. 21%European club minutes0%

Club football in the two years to each valuation date. Longer bar = larger value, not better player.

03

What moves each estimate

The input that separates them most is age: ×1.42 for Thuram (25.2 yrs) against ×0.08 for Gueye (36.7 yrs).

Thuram

Model A starts Thuram at €2.2M and moves the estimate input by input. Appearances raises it most (×1.95). It ends at €41.4M against an observed €38M.

After all 20 inputs Model A arrives at €41.4M (exp 17.539). The observed market value is €38M: residual −0.085, so the observed value is below the estimate (the model over-predicts).

raises the estimate lowers it Model A estimate observed value (dashed line)Log scale: equal lengths are equal multiplications. Inputs are ordered by size of effect, not in any causal sequence. Published SHAP run, served Model A; in-sample.

Gueye

Model A starts Gueye at €2.2M and moves the estimate input by input. League raises it most (×3.15); age lowers it most (×0.08). It ends at €796k against an observed €500k.

After all 20 inputs Model A arrives at €796k (exp 13.587). The observed market value is €500k: residual −0.464, so the observed value is below the estimate (the model over-predicts).

raises the estimate lowers it Model A estimate observed value (dashed line)Log scale: equal lengths are equal multiplications. Inputs are ordered by size of effect, not in any causal sequence. Published SHAP run, served Model A; in-sample.

04

Against the market

Thuram: observed €38M against €41.4M, residual −0.085, so the observed value is below the estimate (the model over-predicts).

Gueye: observed €500k against €796k, residual −0.464, so the observed value is below the estimate (the model over-predicts).

Both estimates come from the served model, which was trained on these players: in-sample figures that sit closer to the market than an honest held-out estimate would. A residual is a disagreement between a model and Transfermarkt, not a finding that either player is over- or under-priced. Full records: Thuram, Gueye.