Move it or lose it: Exploring the relation of defensive disruptiveness and team success

Abstract

Introduction: Due to the increasing number of tracking data available for official matches in different leagues there are new ways to capture the performance of teams. To not rely on notational data, we previously introduced the D-Def (Goes et. al, 2018), an aggregated variable to quantify passing solely based on tracking data. This value captures the change of organisation by a pass (defensive disruptiveness). In this study, we updated the D-Def by including an automated classifier for subunits, instead of using starting formations, and investigated the relation of the D-Def on team success. Methods: Position tracking data of all players and the ball collected during 89 Dutch Premier League matches was used. Alignment of subunits was automatically identified, using a K-Means classifier, for every pass. D-Def was calculated for every pass (N= 63601) as an aggregate in the change in movement as a result of the pass-based team- and line centroids of subunits and surface and spread of the defending team. Team success was evaluated via wins and losses. We excluded 21 matches because they resulted in a draw. The predictive value of the D-Def for success was calculated using logistic regression analysis. Results & Discussion: The regression model achieved a R² of 0.69 which is high in comparison to other key performance indicators in the literature. This shows that the approach previously introduced as a proof of concept is related to match outcome. Therefore D-Def can be a useful tool to evaluate team performance. Conclusions: This study highlights that performance can be predicted through spatio-temporal aggregates based on player tracking data and we do not need to rely on notational data anymore. Reference: Goes FR, Kempe M, Meerhoff LA, Lemmink KAPM (2018). Not every pass can be an assist: a data-driven model to measure pass effectiveness in professional soccer matches. Big Data, DOI: 10.1089/big.2018.0067

The “Hockey” Assist Makes the Difference—Validation of a Defensive Disruptiveness Model to Evaluate Passing Sequences in Elite Soccer

“…This result supports the idea that D-Def can be used to evaluated passing performance. This is in line with earlier studies demonstrating that D-Def can differentiate between good and bad passers on an individual level [ 15 ], and D-Def being a better predictor of the end result of a game in comparison to other key performance indicators [ 18 ]. This connection of D-Def with the end result can now be expanded with the current finding of D-Def showing higher values in successful attacks.…”

“…In this context, other studies showed a higher chance of scoring against an unbalanced defense compared to a balanced defense [ 16 , 17 ]. Earlier studies already revealed that D-Def can differentiate between good and bad passers on the individual level [ 15 ] and is a better predictor of the final result of a match compared to other performance indicators [ 18 ]. However, since the end result of a game is strongly influenced by chance [ 19 ], the relationship of D-Def and success should not solely be traced back to the end result.…”

Attacking Key Performance Indicators in Soccer: Current Practice and Perceptions from the Elite to Youth Academy Level

“…For defenders, it only includes last 6 players on the field plus the goalkeeper based on the longitudinal coordinates or how many players are overplayed in terms of distance between the ball and the center of the opponent's goal. (Memmert et al, 2017), (Rein et al, 2017), (Goes et al, 2019), (Steiner et al, 2019) D-Def (measures the disturbance a pass causes on the defense) (Goes et al, 2018), (Kempe and Goes, 2019) I-Mov (the movement of all opposing players in response to a pass) (Goes et al, 2018), (Kempe…”

Is ball-possession style more physically demanding than counter-attacking? The influence of playing style on match performance in professional soccer

“…Furthermore, from a technical point of view, players are in ball possession 57 times and play 38 passes on average (Forcher et al, 2022d). Lastly, in a tactical context, studies revealed that passes with a higher potential of disrupting the opposing team lead to more successful attacks (Kempe and Goes, 2019;Forcher et al, 2021).…”