The Player Kernel: Learning Team Strengths Based on Implicit Player Contributions
This work addresses a domain-specific problem for sports analytics, offering an incremental improvement in modeling team strengths through player contributions.
The authors tackled the problem of predicting football match outcomes by connecting skill-based models to Gaussian process classification, enabling knowledge transfer from abundant club matches to limited national team matches. They evaluated on Euro 2008, 2012, and 2016 tournaments, but no concrete numbers were provided in the abstract.
In this work, we draw attention to a connection between skill-based models of game outcomes and Gaussian process classification models. The Gaussian process perspective enables a) a principled way of dealing with uncertainty and b) rich models, specified through kernel functions. Using this connection, we tackle the problem of predicting outcomes of football matches between national teams. We develop a player kernel that relates any two football matches through the players lined up on the field. This makes it possible to share knowledge gained from observing matches between clubs (available in large quantities) and matches between national teams (available only in limited quantities). We evaluate our approach on the Euro 2008, 2012 and 2016 final tournaments.