Application of multivariant decision tree technique in high performance football: The female and male corner kick.

Abstract

The use of multidimensional statistical technique based on decision trees is of recent application in sports science. In the case of football, this technique has not yet been sufficiently proven. The aim of the present study was to search for different success models for the corners in the FIFA World Cup 2014 and FIFA Women's World Cup 2015. For this, the statistical analysis focused on the search for classification models for the different criteria considered (shot, shot between the three posts and goal), based on the creation of different decision trees that allow the most important variables to be identified quickly and efficiently. For this, 1117 corners were collected between the two competitions, performed in 116 international matches. It has been possible to establish multivariate models for the "shot" and "shot between the three posts" criteria, allowing, in some cases, to quadruple the potential for offensive success. On the other hand, we have been able to identify significant differences in the male and female model of execution. These findings suggest the need to continue deepening the study of tactical behavior in women's soccer from a multivariate perspective, and also propose a better optimization of the management and training of this type of actions for both male and female football. In addition, it has allowed to test the decision tree statistical technique in the analysis of high performance football, with satisfactory results and of great relevance in the applied field.