Data-driven detection of counterpressing in professional football

Abstract

Detecting counterpressing is an important task for any professional match-analyst in football (soccer), but is being done exclusively manually by observing video footage. The purpose of this paper is not only to automatically identify this strategy, but also to derive metrics that support coaches with the analysis of transition situations. Additionally, we want to infer objective influence factors for its success and assess the validity of peer-created rules of thumb established in by practitioners. Based on a combination of positional and event data we detect counterpressing situations as a supervised machine learning task. Together, with professional match-analysis experts we discussed and consolidated a consistent definition, extracted 134 features and manually labeled more than 20, 000 defensive transition situations from 97 professional football matches. The extreme gradient boosting model—with an area under the curve of $$87.4\%$$ 87.4 % on the labeled test data—enabled us to judge how quickly teams can win the ball back with counterpressing strategies, how many shots they create or allow immediately afterwards and to determine what the most important success drivers are. We applied this automatic detection on all matches from six full seasons of the German Bundesliga and quantified the defensive and offensive consequences when applying counterpressing for each team. Automating the task saves analysts a tremendous amount of time, standardizes the otherwise subjective task, and allows to identify trends within larger data-sets. We present an effective way of how the detection and the lessons learned from this investigation are integrated effectively into common match-analysis processes.

Automatic Detection Algorithm of Football Events in Videos

“…It measures the timeliness of the method by recording the time it takes to extract features. The event detection time is 64.79% of reference A [ 24 ], 48.89% of reference B [ 25 ], and 37.23% of reference C [ 26 ]. The reason is that the proposed method first filters 13 semantic features for each different event by clustering.…”

“…Among them, the hidden state n is taken from 1 to 4, from small to large. This algorithm model is compared with literature A [ 24 ], literature B [ 25 ], and literature C [ 26 ] proposed by scholars in related fields. The advantages of model performance under different models are compared.…”

Identifying Soccer Teams’ Styles of Play: A Scoping and Critical Review

“…Many playing styles, such as those that concern the first sub-phase of the attack (the “build up from the back”) and others, have yet to be identified in a factor-based study. As examples, we mention the offside trap, which is a very common tactical tool of coaches [ 66 , 67 , 68 , 69 ], the passing tempo that gives very useful information about the playing style of a team [ 12 , 40 , 70 ], the counter-pressing [ 71 , 72 ] and so on. Further, only two studies employing factor analysis with PCA [ 47 , 50 ] had access to physical performance variables.…”

Expected Goals Prediction in Football using XGBoost

“…Bauer et al [6] detected defensive traits to reduce goal threat. Model that was deployed is the gradient boosting algorithm.…”