# Soccer Team Vectors

## TL;DR

STEVE is a method for learning vector representations of soccer teams based on match history, enabling tasks like market value estimation, similarity search, and ranking, with superior performance demonstrated.

## Contribution

Introduces STEVE, a novel approach for creating meaningful team vectors from match data, improving on existing methods for soccer team analysis.

## Key findings

- Outperforms competitors in team market value estimation
- Enables effective similarity search among teams
- Supports accurate ranking of soccer teams

## Abstract

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.