Home/Soccer Analytics/Archetype-Based Player Profiling

Archetype-Based Player Profiling

RecruitmentLevel 2 — Intermediate

What It Is

Instead of asking a coach what they want abstractly, you ask them to name 3-5 real players (past or present, anywhere in the world) who exemplify what they need at a position. You then build a statistical profile from those archetype players — finding what they share in the data — and use that profile as the search template for recruitment. The archetype players ground the search in observable reality rather than abstract description.

Correct Execution

Process: (1) ask coach to name archetype players for each role they need to fill; (2) pull data for all named archetypes; (3) identify 4-8 metrics where the archetypes cluster significantly above or below average; (4) those metrics become the profile weights. The profile should describe the archetypes well — if it doesn't rank them highly, the metrics are wrong. Not limited to same league or era — a historic archetype is valid as long as the data exists.

Progression Levels

Diagnostic Tree

Coaching Cues

  • "Tell me the best players you've ever seen in this role — anywhere, any era. Now let's see what they have in common." — Ted Knutson, 2018
  • "Archetypes are ground truth. If the model doesn't recover them, fix the model."

Common Errors

  1. Taking archetypes from one league only: A coach who's only named Serie A players may be unconsciously filtering for Serie A style; ask if they'd also include players from other leagues/eras.
  2. Not checking if the profile correctly ranks the archetypes: If the resulting model doesn't score the named archetypes highly, the metric selection is wrong.

Edges

Conventional Wisdom Is Wrong

Positional Averages Hide 3-4 Distinct Archetypes Within Every Position

"Average center-back" or "average right-back" doesn't exist as a meaningful concept. Within each nominal position, 3-4 distinct archetypes exist with fundamentally different statistical profiles (e.g., progressive ball-playing CB vs. aerial-dominant CB vs. covering sweeper CB). Percentile rankings against "all center-backs" penalize specialists by diluting their elite dimensions with irrelevant comparisons. A ball-playing CB in the 40th percentile for aerial duels isn't bad — they're being measured against aerially-dominant CBs who play a different game.

What most people do
Normalize metrics within the full position group. Compare all CBs to all CBs.
What the best do
First cluster the position into archetypes. Then normalize within archetype. Evaluate a ball-playing CB against other ball-playing CBs, not against aerial monsters. The comparison population determines the conclusion.
Why it's an edge: Archetype-blind evaluation produces systematic errors: it underrates specialists and overrates generalists. The best player at a specific archetype may look average when measured against the full position group.
How to exploit: Define 3-4 archetypes per position from cluster analysis. For each recruitment target, identify their archetype first, then rank within that archetype. A player who is 95th percentile within their archetype is more valuable than a player who is 70th percentile across all position members.
Ted Knutson, multiple StatsBomb presentations. Archetype-based profiling as a core scouting methodology.

Sources

  • Ted Knutson, Barcelona Coach Analytics Summit, YouTube, 2018-11-18 — described archetype interview methodology; used the Jorginho replacement example at Napoli to illustrate player similarity search