<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In the growing field of data analysis in soccer tracking data is analyzed utilizing increasingly complex methods to account for the dynamic, multifactorial nature of the game. One promising approach is the Success-Score combining ball control and space control. The resulting metric is hypothesized to indicate performance levels and to distinguish performance from playing style. Position datasets from one season of the German Bundesliga were analyzed by calculating Success-Scores based on different interval lengths for two different areas. The relative goalscoring frequency above resp. below the 80<sup>th</sup> percentile and the rank order correlation between goals and Success-Scores was used to assess the relevance of the Success- Score for goalscoring. The influence of the Success-Score on match outcome, accounting for possession and opponent quality was analyzed via mixed linear models. Results indicated a relation between goalscoring and the Success-Scores, as well as a considerable influence of the Success-Scores on match outcome. The mixed linear models allowed to conclude that Success-Scores capture performance rather than just playing style. The results highlight the potential of the general concept of the Success-Score, combining space and ball control. However, the practical value of the Success-Score in its current implementation appears limited and requires further development.</p>
</abstract>

In the growing field of data analysis in soccer tracking data is analyzed utilizing increasingly complex methods to account for the dynamic, multifactorial nature of the game. One promising approach is the Success-Score combining ball control and space control. The resulting metric is hypothesized to indicate performance levels and to distinguish performance from playing style. Position datasets from one season of the German Bundesliga were analyzed by calculating Success-Scores based on different interval lengths for two different areas. The relative goalscoring frequency above resp. below the 80th percentile and the rank order correlation between goals and Success-Scores was used to assess the relevance of the Success- Score for goalscoring. The influence of the Success-Score on match outcome, accounting for possession and opponent quality was analyzed via mixed linear models. Results indicated a relation between goalscoring and the Success-Scores, as well as a considerable influence of the Success-Scores on match outcome. The mixed linear models allowed to conclude that Success-Scores capture performance rather than just playing style. The results highlight the potential of the general concept of the Success-Score, combining space and ball control. However, the practical value of the Success-Score in its current implementation appears limited and requires further development.

The Success-Score in Professional Football: a metric of playing style or a metric of match outcome?

International Journal of Computer Science in Sport

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

In the growing field of data analysis in soccer tracking data is analyzed utilizing increasingly complex methods to account for the dynamic, multifactorial...

The Success-Score in Professional Football: a metric of playing style or a metric of match outcome?

Online veröffentlicht: 18. Apr. 2024

Seitenbereich: 54 - 79

DOI: https://doi.org/10.2478/ijcss-2024-0004

Schlüsselwörter
KEY PERFORMANCE INDICATOR, BALL POSSESSION, DOMINANT REGIONS, FOOTBALL, MIXED LINEAR MODELS

© 2024 David Brinkjans et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The Success-Score in Professional Football: a metric of playing style or a metric of match outcome?

Online veröffentlicht: 18. Apr. 2024

Seitenbereich: 54 - 79

DOI: https://doi.org/10.2478/ijcss-2024-0004

SchlüsselwörterKEY PERFORMANCE INDICATOR, BALL POSSESSION, DOMINANT REGIONS, FOOTBALL, MIXED LINEAR MODELS

© 2024 David Brinkjans et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Schlüsselwörter
KEY PERFORMANCE INDICATOR, BALL POSSESSION, DOMINANT REGIONS, FOOTBALL, MIXED LINEAR MODELS