Identification of Explanatory Variables in Possession of the Ball in High-Performance Women's Football

Artificial intelligence applications in the football codes: A systematic review

Artificial Intelligence (AI) is increasingly being adopted across many domains such as transport, healthcare, defence and sport, with football codes no exception. Though there is a range of potential benefits of AI, concern has also been expressed regarding potential risks. An important first step in ensuring that AI applications in football are usable, beneficial, safe and ethical is to understand the current range of applications, the AI models adopted and their proposed functions. This systematic review aimed to identify different applications of AI across football codes to synthesise current knowledge and determine whether potential risks are being considered. The systematic review included 190 peer-reviewed articles. Nine areas of application were found ranging from athlete evaluation and event detection to match outcome prediction and injury detection and prediction. In total, 27 different AI models were identified, with artificial neural networks the most frequently applied. Five AI assessment metrics were identified including specificity, recall, precision, accuracy and F1-score. Four potential risks were identified, concerning data security, usability, data biases and inappropriate athlete load management. It is concluded that, though a wide range of AI applications currently exist, further work is required to develop AI for football and identify and manage potential risks.

Future horizons in the analysis of technical-tactical performance in women's football: a mixed methods approach to the analysis of in-depth interviews with professional coaches and players

Introduction

Scientific knowledge about the criteria that determine success in women's football is beginning to develop.

Methods

This study was carried out with the aim of detecting regularities in the offensive success in elite women's football, as well as carrying out an interrelational analysis of linked behaviors, based on in-depth interviews with professional coaches and players. Eight in-depth interviews were conducted with professional Spanish coaches and players. The interviews were analyzed by indirect observation from a process of "quantitizing," through the construction of an indirect observation ad hoc instrument. The segmentation of the transcription of the interviews was carried out in textual units, and the creation of a matrix of codes. Two types of analysis were performed: first, a lag sequential analysis (LSA) was performed and, then, a polar coordinates analysis (PCA), which allowed to find, respectively, a wide number of established communicative patterns with offensive performance in women's football, as well as an interrelational map between the established codes.

Results

The results obtained allowed us to suggest a statistically significant association between success in women's football and criteria such as the physical characteristics of a particular player, the individual action space, the duration of the attack, the type of dynamic start, individual and collective technical and tactical aspects, decision making and the type of attack used.

Discussion

Based on these results, the influence of these criteria on performance in women's soccer can be studied in future studies. In addition, with the aim of increasing the validity of these conclusions, new studies on this subject may be carried out following strategies such as the Delphi Method.

Deciphering the offensive process in women's elite football: a multivariate study

Over the last few years there has been considerable increase in scientific knowledge about women's football. However, the tactical and tactical-strategic aspects have not yet been sufficiently covered in scientific literature. Therefore, this work proposed the following aims: to describe how the offensive phase is produced in women's football, to identify the significant statistical criteria that may be modulating success in attack, and finally to propose different predictive success models, with the ultimate aim of passing this knowledge on to the applied field. The observational methodology was used, one of the most appropriate methodologies for the analysis of motor behaviors in sport. The units of analysis collected and analysed were 6,063 attacks carried out during the FIFA Women's World Cup Canada 2015 and France 2019. The available results demonstrate that, on the one hand, offensive team actions are ineffective (almost 70% finish unsuccessfully), but criteria such as the start form of the attack, zone of ball possession, partial match result or ball possession time are statistically significant criteria that modulate attack success (goal, shot or pass into the area). Lastly, the multivariate results allow us to propose a theoretical model, passing the probability of success from 31% in the absence of a model, to a theoretical auction probability of 52.6%, based on fast attacks with the intervention of few players, and with possession zone in the opposite field. These results could be directly transferred to the practical field where trainers and technical bodies can put this information into practice in training sessions or matches.