The Problem
The Old Way
INTUITION-BASED SCOUTING
NO TACTICAL FIT PREDICTION
HIGH TRANSFER UNCERTAINTY
ELITE-CLUB BIAS
HIDDEN POTENTIAL OVERLOOKED
NO ADAPTATION METHODOLOGY
The New Way
DATA-DRIVEN EVALUATION
PERFORMANCE FORECASTING BY TEAM STYLE
CONTEXT-AWARE TRANSFER PLANNING
FIT-BASED SUGGESTIONS ACROSS TIERS
TACTICAL COMPATIBILITY REVEALS VALUE
STANDARDIZED MATCHING ALGORITHM
Technical Description
Vectorization & Clustering
-
Each player and team is represented by a normalized vector of features (e.g., playing style, tactical behavior, role).
-
Clustering algorithms (e.g., K-Means) are applied to group similar players and teams into tactical clusters.
Distance Calculation
-
For a given player and team pair, a distance score d(Pi, Tj) is calculated to measure tactical fit.
-
A lower score indicates stronger compatibility between the player's style and the team’s tactics.
Growth Projection
The algorithm computes the Market Growth Index (MGI) based on historical ELO trends, estimating how much the player’s performance could evolve post-transfer.
Performance Delta Estimation
-
The expected performance variation ΔRij is calculated by combining:
-
Tactical Fit Distance
-
Growth Potential (MGI)
-
-
Output: A ranked list of teams with predicted performance gains or losses for the target player.
Details:
The first graph centers on a single player and shows directional arrows pointing toward various potential clubs.
Green arrows represent positive performance gains (e.g., +12%), while red arrows signal projected underperformance (e.g., –11%).
It offers a clear view of which clubs could optimize the player’s potential and which environments might hinder it, based on tactical compatibility.
The second visualization map show both teams and players in a 2D tactical space (X and Y dimensions).
Each point represents a player or team cluster based on tactical style. The grey arrows show the predicted performance variation if a player moves to a different tactical environment.
Distances indicate tactical compatibility — the closer the player is to the team cluster, the better the fit. Labels like “Fit” and “Gain” quantify the expected improvement in performance if the transfer occurs.
.png)
.png)
"There are no bad players — only players in the wrong tactical ecosystem."
WINNING quantifies adaptation, identifies ideal environments, and unlocks full player potential through data-driven contextual intelligence.
Other Objetives
Minimize Recruitment Errors
Reduce recruitment errors by basing decisions on objective compatibility between player profiles and tactical systems.
Objective
Preventive
Identify Underused Players With Tactical Potential
Optimize scouting by identifying players who could perform better in a different tactical context.
Opportunistic
Insightful
Reveal Hidden Value Through Team-Fit Analysis
Uncover hidden value by guiding under-the-radar players toward environments that maximize their potential.
Strategic
Scalable
Explain Underperformance Via Contextual Mismatch
Improve tactical understanding by explaining why certain players underperform and where they could fit better.
Diagnostic
Clarifying
Forecast Performance Across Styles And Teams
Interpret performance data in context to better project outcomes across different playing styles and systems.
Predictive
Contextual