Understanding gender differences in professional European football through machine learning interpretability and match actions data

Abstract

After the great success of the Women’s World Cup in 2019, several platforms have started identifying the reasons for gender inequality in European football. Even though these inequalities emerge from a variety of key aspects in the modern sport, we focused on the game and evaluated the main differential features of European male and female football players in match actions data under the assumption of finding significant differences and established patterns between genders. A methodology for unbiased feature extraction and objective analysis is presented based on data integration and machine learning explainability algorithms. Female ($$n_0 = 1511$$ n 0 = 1511 ) and male ($$n_1 = 2703$$ n 1 = 2703 ) data points were collected from event data and categorized by game period and player position. We set up a supervised classification pipeline to predict the gender of each player by looking at their actions in the game. The comparison methodology did not include any qualitative enrichment or subjective analysis to prevent biased data enhancement or gender-related processing. The pipeline included three representative binary classification models; A logic-based Decision Trees, a probabilistic Logistic Regression and a multilevel perceptron Neural Network. Each model tried to draw the differences between male and female data points, and we extracted the results using machine learning explainability methods to understand the underlying mechanics of the models implemented. The study was able to determine pivotal factors that differentiate each gender performance as well as disseminate unique patterns by gender involving more than one indicator. Data enhancement and critical variables analysis are essential next steps to support this framework and serve as a baseline for further studies and training developments.

The Value of Meteorological Data in Optimizing the Pattern of Physical Load—A Forecast Model of Rowing Pacing Strategy

“…Just input the race date and time, race location, track number and boat type, and that will provide the weather forecast results of the selected moment (including the highest temperature, the lowest temperature, the probability of precipitation, wind speed and direction), as well as the recommended pacing strategy (speed and paddle frequency) for each segment of Q1–Q4. Following the visual way of presenting the methodology in Garnica-Caparrós and Memmert (2021) [ 37 ], the methodology figure workflow is presented in Figure 3 . After more than 10 epoch training, our model can be applied to the actual weather forecast.…”

A data-driven framing of player and team performance in U.S. Women's soccer

“…In addition, most of the data in the comparative studies were from small samples and lower quality sources. With data quality and reliability considered to be highly important in soccer analytics ( 33 ), reputable data collection companies such as StatsBomb and Stats Perform (formerly known as Opta) should be used. StatsBomb, for instance, boasts one of the most extensive public archives of detailed soccer event data that it publicly shares to promote research in the field.…”

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

“…Despite the recent growth of scientific knowledge, the available evidence is still scarce. For this reason, it is not possible to know if everything we know about men’s football performance can be applied to play in women, taking into account the differences in play between the two sexes ( Bradley et al, 2014 ; Casal et al, 2021 ; Garnica-Caparrós and Memmert, 2021 ). Answering this question is considered necessary since it can allow professionals in this sport to apply the knowledge acquired about men’s football to their own sports specialty ( Okholm Kryger et al, 2021 ).…”