Sports has seen an increase in data produced, primarily due to tracking and wearable sensors. One might assume that a rise in data and metrics in sports would help athletes and coaches to support decisions - But this is hard said than done, as currently, there is an overwhelming amount of data to analyse. In other application areas, Machine learning methodologies have been employed successfully to help practitioners with these problems. Such examples can be seen in preventive maintenance, recommendation systems and others. In many of these applications, domain and technical expertise were required. Machine learning in sports is a relatively new field and holds big potential for innovation. This summer school aims to accelerate the development of skills of the participants necessary to develop machine learning models and methodologies applied to sports through a cross-disciplinary approach. At the end of the course, you will become an Olympian in Sports Analytics!
Course leader
Leonid Kholkine
Target group
Anyone with experience in either sports and a strong interest in Machine Learning or experience in Machine Learning and a strong interest in sports. PhD students, researchers and professionals working at the intersections of both fields are encouraged to apply.
Participants need to know the basics of Python before the course or to be willing to learn before the beginning of the course.
Fee info
EUR 250: Fee includes course materials, lunches, coffee breaks, social activities and a networking dinner. It does not include travel and accommodation.
For further information, please click the "LINK TO ORIGINAL" button below.