Machine Learning in Sports 101

Abstract

Data about sports have long been the subject of research and analysis by sports scientists. The increasing size and availability of these data have also attracted the attention of researchers in machine learning, computer vision and artificial intelligence. However, these communities rarely interact. This seminar aimed to bring together researchers from these areas to spur an interdisciplinary approach to these problems. The seminar was organized around five different themes that were introduced with tutorial and overview style talks about the key concepts to facilitate knowledge exchange among researchers with different backgrounds and approaches to data-based sports research. These were augmented by more in-depth presentations on specific problems or techniques. There was a panel discussion by practitioners on the difficulties and lessons learned about putting analytics into practice. Finally, we came up with a number of conclusions and next steps. Seminar October 10-15, 2021-http://www.dagstuhl.de/21411 License Creative Commons BY 4.0 International license © Ulf Brefeld, Jesse Davis, Martin Lames, and Jim Little Sports has become an incredibly data rich field with the advent of data sources such as event data (e.g., time and locations of actions), tracking data (i.e., positional data), and athlete monitoring (e.g., bio-sensors, IMUs, GPS). These data are commonly and widely collected across multiple different sports, both on a professional and recreational level. The advent of such data raises the need to exploit the collected data both from the theoretical (e.g., sports modeling) as well as practical (e.g., training in top level sports) perspective. Problem-solving solutions can only be provided by an interaction between the sports science & informatics (S&I) and the machine learning (ML) communities. Machine learning is emerging as a powerful, new paradigm for sports analytics, as it provides novel approaches to making sense