Actions Speak Louder than Goals

Abstract

Assessing the impact of the individual actions performed by soccer players during games is a crucial aspect of the player recruitment process. Unfortunately, most traditional metrics fall short in addressing this task as they either focus on rare actions like shots and goals alone or fail to account for the context in which the actions occurred. This paper introduces (1) a new language for describing individual player actions on the pitch and (2) a framework for valuing any type of player action based on its impact on the game outcome while accounting for the context in which the action happened. By aggregating soccer players' action values, their total offensive and defensive contributions to their team can be quantified. We show how our approach considers relevant contextual information that traditional player evaluation metrics ignore and present a number of use cases related to scouting and playing style characterization in the 2016/2017 and 2017/2018 seasons in Europe's top competitions.

Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis

“…In Fig. 4 (right), three teams (final ranking) are considered: Manchester City (1), Chelsea (5), and Newcastle United (10). As Fig.…”

“…Football 5 has simultaneously been an influential sport and important industry around the globe [15]. Estimate has shown that the FIFA World Cup Qatar 2022 entertained over 5 billion viewers 6 , and it has also been established to be a pillar industry for countries like Italy and Great Britain [35].…”

SoccerMix: Representing Soccer Actions with Mixture Models

“…Moreover, the data also contains extraneous information such as changes in weather that are not crucial for analysis. The SPADL representation [6] addresses these concerns by converting event streams to a uniform representation designed to facilitate analysis. 2 Hence, we first transform our data into this format.…”

How does AI play football? An analysis of RL and real-world football strategies

“…Therefore, it is only recently that a data-driven approach has started to gain attention. Nevertheless, numerous approaches, from the simple aggregation of individual/team play statistics (Novatchkov and Baca, 2013), to complex methods, such as those that use gradient boosting to model the value of actions (Decroos et al, 2018a). In general one can observe two different types of analysis.…”

“…In this case, an action is usually valued then aggregated by either player or team. (Decroos et al, 2018a) assigned values to on-ball action actions by measuring their effect on the probabilities that a team will score. In turn, (Fernandez and Bornn, 2018) proposed a method to value off the ball actions by estimating pitch value with a neural network.…”