Soccer Team Vectors
This work provides a domain-specific tool for soccer analytics, offering incremental improvements in team representation.
The authors tackled the problem of representing soccer teams as vectors for machine learning tasks, and their method STEVE outperformed competitors in team market value estimation.
In this work we present STEVE - Soccer TEam VEctors, a principled approach for learning real valued vectors for soccer teams where similar teams are close to each other in the resulting vector space. STEVE only relies on freely available information about the matches teams played in the past. These vectors can serve as input to various machine learning tasks. Evaluating on the task of team market value estimation, STEVE outperforms all its competitors. Moreover, we use STEVE for similarity search and to rank soccer teams.