Admission requirements
The student is expected to be familiar with key concepts of data mining or machine learning at the Bachelor’s level, and have been exposed to basic statistics. Necessary key concepts in data mining include classification, regression, clustering, cross-validation, overfitting, sampling, feature construction, ROC-curves. The Leiden CS Bachelor’s course on Machine Learning provides such basic understanding, but many similar courses exist elsewhere.
Description
The course aims to outline the (growing) role of data science in sports. Through various technological advances over the last years, it’s becoming easier to collect substantial datasets in sports, and practitioners are beginning to see the added benefit of collecting and analysing such data to achieve their goals. These goals might include optimizing one’s training efforts, personalising training schedules to the individual needs, understanding injury incidence and its prevention, optimizing the strategy in team sports and making data-driven tactical decisions. The course offers an introduction into the key concepts of sports science (including physiology and testing methods), an understanding of the basic questions to be answered in a range of sports disciplines, what types of data to expect or collect, and the specific data science techniques that are applied to these settings. The data science aspect of the course will focus on time series techniques, feature construction, aggregation, and subgroup discovery.
Course objectives
At the end of the course, the student should be able to…
list the basics of sports science and human physiology.
explain the role of the three energy systems in (human) exercise.
list analytical tools for analysing sports data, notably spatial and temporal aggregation.
explain the sports data science cube and position a given SDS application in this cube.
apply data science techniques to different forms of data, including sensor, IMU, video, position and journal data.
explain in detail the role of data in selected sports, at least speeds skating and road cycling.
critically assess the content and quality of scientific SDS publications and explain or discuss said papers with fellow students.
analyse a new SDS application in a given sports discipline and execute a data analysis exercise.
explain a selected analytical approach and communicate the findings in a report aimed at sports practitioners.
Timetable
The most recent timetable can be found at the Computer Science (MSc) student website.
You will find the timetables for all courses and degree programmes of Leiden University in the tool MyTimetable (login). Any teaching activities that you have sucessfully registered for in MyStudyMap will automatically be displayed in MyTimeTable. Any timetables that you add manually, will be saved and automatically displayed the next time you sign in.
MyTimetable allows you to integrate your timetable with your calendar apps such as Outlook, Google Calendar, Apple Calendar and other calendar apps on your smartphone. Any timetable changes will be automatically synced with your calendar. If you wish, you can also receive an email notification of the change. You can turn notifications on in ‘Settings’ (after login).
For more information, watch the video or go the the 'help-page' in MyTimetable. Please note: Joint Degree students Leiden/Delft have to merge their two different timetables into one. This video explains how to do this.
Mode of instruction
The course will offer a rich mixture of instruction modes, including:
introductory lectures on sports science and specific data science techniques
seminar-like presentation and discussion of selected papers
guest lectures from invited experts from the fields of cycling, speed skating, volleyball, …
field trips to various training locations, for example Thialf (largest Dutch ice stadium) or the Amsterdam Human Performance Lab.
data science exercise based on real data from elite sports.
Assessment method
The grading of the course will be based on the following components:
written exam (multiple choice), 30%
paper presentation and participation, 30%
data science exercise execution, 40%
Reading list
To be determined.
Registration
Students will have to register in advance for this course. At most 30 students can participate each year. In the case more than 30 students register for the course, students primarily registered at Leiden University will get precendence. Next, students who attempted to register in the previous year, and could not participate the, get precedence. Next, students are admitted on a first-come first-serve basis.
Every student has to register for courses with the new enrollment tool MyStudyMap. There are two registration periods per year: registration for the fall semester opens in July and registration for the spring semester opens in December. Please see this page for more information.
Please note that it is compulsory to both preregister and confirm your participation for every exam and retake. Not being registered for a course means that you are not allowed to participate in the final exam of the course. Confirming your exam participation is possible until ten days before the exam.
Extensive FAQ's on MyStudymap can be found here.
Contact
- dr. Arno Knobbe; phone: +31624612560
Remarks
The course will run for the entire Spring semester, running from February to June. In a weekly timeslot, lectures will be provided, papers will be discussed, training facilities will be visited and you will work on a hands-on data science project in a specific sport.