Advanced data analytics in soccer

• Activity Number: 144
• Type: Invited
• Date/Time: Monday, August 4, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Sports
• Author(s): Paolo Lisboa*+ and Hector Ruiz and Paul Neilson and Shayne Hall and Warren Gregson
• Companies: Liverpool John Moores University and Liverpool John Moores University and Prozone Sports and Prozone Sports and Liverpool John Moores University

Abstract

Performance analysis in soccer is entering a new era where current univariate measurements and summary statistics are being complemented with multivariate statistical analysis leading to the identification and characterisation of team playing styles while in possession of the ball. The talk will outline the key stages in a hierarchical model using event tracking to define higher level team playing concepts, from which playing style is automatically inferred from annotated match data. This enables objective comparisons to be made between teams with regard to tactical play and has considerable potential for further detailed assessments of a range of performance indicators for both teams and individual players.