Skip to Main Content

Football Performance Analysis Solutions

Identifying tactically relevant insights, in addition to underlying performance trends, are key challenges faced by analysis departments. Powered by tracking and event data, Edge Analysis applies unique AI models to unlock objective, dynamic and predictive insights to enhance an analyst’s pre-match processes and their assessment of upcoming opposition.


Edge analysis

Match Analysis

Featuring AI-assistive modules designed to support the typical workflow adopted by a performance analysis department, Edge Analysis helps analysts build a better understanding of a team’s playing characteristics, ball distribution, player roles and changes to team shape during different phases, which are contextualised through Stats Perform’s unique Playing Styles framework.

03:48 Bayer 04 Leverkusen on Edge Analysis
02:59 Paul Heckingbottom Dives into Edge Analysis
02:35 Croatia Analyst Marc Rochon on Edge Analysis
02:00 Mark Warburton on Edge Analysis & the Responsibilities of Data Providers
Play Edge Analysis at Bayer 04 Leverkusen
Edge Analysis at Bayer 04 Leverkusen (03:48)
Play Paul Heckingbottom Dives into Edge Analysis
Paul Heckingbottom Dives into Edge Analysis (02:59)
Play Croatia Analyst Marc Rochon on Edge Analysis
Croatia Analyst Marc Rochon on Edge Analysis (02:35)
Play Mark Warburton on Edge Analysis & the Responsibilities of Data Providers
Mark Warburton on Edge Analysis & the Responsibilities of Data Providers (02:00)

Edge Analysis key features

Shape Analysis

Over the course of a match, a team’s shape is constantly evolving as a result of tactical changes and the game state. Edge Analysis layers AI on top of tracking data, so an analyst can quickly understand how team shape evolves during specific phases or in a particular context.

  • Provides a more accurate indication of a team’s overall shape compared to average positions.
  • Helps identify the most likely shape to be adopted by each upcoming opponent.
  • Reveals movement errors and open spaces.
  • Adds an additional layer of meaning with game context, described through the Stats Perform Playing Styles framework.
  • Shapes are linked to outcomes, such as shots and lost possession, to identify successful and unsuccessful scenarios.


Edge Analysis key features

Influential Players & Roles

Knowing how a player or role contributes to a team ultimately helps devise a game plan, based on eliminating an opposition threat or exploiting a vulnerability. Edge Analysis incorporates a detailed breakdown of the different players and roles in a club’s squad, using AI-derived models to quantify their contribution to generating scoring opportunities.

  • To eradicate the limitations of assessing players by position, players are categorised based on their role within their team’s wider playing style.
  • The effectiveness of each player’s on-the-ball actions is quantified using a Possession Value (PV) model, highlighting which of their events increase or decrease their team’s chances of scoring in the next 10 seconds.
  • Every player is assigned a net PV rating. This highlights standout players who contribute the most progressive actions, in addition to players recording low regressive actions.
  • By narrowing down the players and roles which are most influential in an opposition’s playing style, analysts can start evaluating ways of minimising their on-field influence.


Edge Analysis key features

Pattern Analysis

Identifying an opponent’s recurring passing chains, which result in successful ball progression and chance creation, can help devise strategies for disrupting a team’s most effective ways of moving the ball into threatening areas. Edge Analysis automatically detects a team’s most dangerous passing chains, based on how they increase their likelihood of a team scoring.

  • Recurring chains are clustered, automatically detecting specific patterns of play.
  • To assist analysts with identifying the effectiveness of specific chains, each cluster is assigned a Possession Value, based on how they increase goal probability.
  • Users can search for chains starting and ending in different zones of the pitch to help understand how teams progress the ball from specific areas.
  • To provide additional context, a tracking-powered pressure halo determines the level of pressure a player is under when they move the ball during a chain.
  • Further filtering options enable an analyst to isolate chains which involve influential players and passes which are harder to complete, based on an Expected Pass Completion (xP).

SPEAK with our team

Edge Analysis key features

Advanced Set Play Analysis

Matches can be won or lost on set plays. Edge Analysis enables analysts to conduct in-depth analysis from every corner and attacking free kick routine utilised during the season, using tracking data, in a matter of minutes.

  • Outcome analysis allows for identification of set-piece strengths and weaknesses.
  • Provides insights on delivery zones, types of deliveries, players’ running patterns and interactions to identify offensive or defensive strategies.
  • Identifies the zones generating the best quality chances, based on expected goals (xG).
  • Speeds up the set-piece analysis process.

SPEAK with our team


Spatial Search

Match tagging is time consuming and repetitive. Edge Analysis incorporates a Spatial Search, which allows an analyst to find various events within customised pitch zones and specific playing styles for a team or individual players.

  • Pair objective analysis with guidance that hones in on an opponent’s strengths and weaknesses, such as the most dangerous playing styles for key players and the zones from which they pose the greatest threat.
  • Enhance and expedite the way full-match footage is analysed through an AI lens with features such as Ball-in-Play mode and a detailed match timeline, highlighting playing styles and key events.


Get Access to Edge Analysis

Find out how Stats Perform’s revolutionary match analysis system can provide deeper insights and improved strategies for your team.