Prof. Paulo Lisboa
Head of the Engineering and Technology Research Institute
Liverpool John Moores University, UK
Advances in data capture and cheap computer processing have made the analysis of data ubiquitous in sport and potentially of value for gaining a competitive advantage. Simple visualization methods readily show player segmentation according to position, from annotated match data. Yet, in-match measurements are made at increasingly fast sampling rates – how much information can be reliably derived from this avalanche of data?
The talk will focus on multivariate analysis to generate actionable insights of potential value to football professionals. For instance, team formation is well known and an obligatory part of match preparation. However, what formation patterns actually arise in actual games? Unsupervised methods give an answer to this. Alternative approaches are more powerful for gaining predictive insights into the structure of data. Among them conditional independence maps are powerful tools to map correlated data without redundancy. Examples will be given in relation to a key area of current interest, modelling injury risk.
A more complex but still preliminary study involves segmenting periods of possession according to playing style. Even though this study deals with a fundamental aspect of play, it highlights the need for a more systematic taxonomy of playing styles, which builds on clustering and requires both knowledge discovery from data and interpretation by panels of experts. It also highlights the power that even relatively simple methods can provide for tactical profiling in professional football and, with it, the ability to quantify changing dynamics in football games.
Paulo Lisboa is Full Professor, Head of Department of Applied Mathematics and Head of the Engineering and Technology Research Institute at Liverpool John Moores University (UK). His research focus is advanced data analysis for decision support, in particular applications to personalised medicine, public health, sports analytics and digital marketing. Professor Lisboa is former chair of the Horizon2020 Advisory Group for Societal Challenge 1: Health, Demographic Change and Wellbeing, providing scientific advice to the world’s largest coordinated research programmes in health. He has extensive experience in editorial and peer review roles in journals and research funding bodies worldwide.