ABSTRACT
When predicting the outcome of soccer matches, it is important to know the relative strengths of the teams involved. However, determining the relative strength of competing teams can be difficult in competitions that do not employ a traditional league structure, such as knockout cup tournaments. This chapter investigates ranking systems that can be used to give an indication of the relative strengths of soccer teams and players, with three popular methods: the Colley, Massey, and Elo algorithms, introduced. In particular, the chapter shows how these ranking systems can be implemented in R and applied to soccer competitions. In addition, the concept of tau distance is introduced, which can be used to evaluate differences in ranking order.
