Teaching performance analysis: essential skills andlearning outcomes

In the age of machine learning, traditional performance analysis courses face challenges such as declining student interest and increasing competition from courses within the respective study programmes. At the same time, courses must accommodate increasingly heterogeneous groups of students, both in terms of background, interests and mathematical ability. In this paper, we present a personal perspective on teaching performance evaluation techniques. We argue that stochastic modelling should be the focus in a performance analysis course and that stochastic analysis techniques are a means to an end to solve performance problems, not the main focus.