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…

Lead story · Research

The gap runs the other way

A model that never sees nationality still misses one group in one direction: non-UEFA players' market values sit about 10% above its estimates, relative to UEFA players in the same leagues (+0.093 log units). Without league and club, +0.164.

Read · 7 chapters →

+0.093

signed residual gap, non-UEFA minus UEFA, within leagues, log units

95% intervals · the thin line is zero, no gap · not evidence of discrimination

Head-to-Head

Two players in the same position, on one scale: the market, the model and what separates them.

Valuation

One estimate, input by input. The line is each valuation journey; the dashed line is the observed value.

Market

Patterns across the fourteen covered leagues, from the held-out error tables.

Fourteen leagues, one price scaleThe median Premier League player is valued at €18M. In 9 of the fourteen covered leagues the median player sits below €2M. What one model makes of that spread.

Player Spotlight

Immersive features built around a player's image and season.

Not published

Spotlights are built around licensed photography and match-by-match data. Neither is cleared for this build, so none are published.

  • Licensed cutout photography, cleared for each player (the asset pipeline accepts CC0, public-domain and CC BY / BY-SA images).
  • Match-by-match data for a season narrative, beyond the two-year totals the model uses.
  • Valuation history, which arrives with the full local player export.
Long read · ResearchHow FairValue worksData, models, validation, explainability and limits: the technical account, printed on paper.