Technical–tactical differences between female and male elite football: A data mining approach through neural network analysis, binary logistic regression, and decision tree techniques

  1. Iyán Iván-Baragaño 2
  2. Rubén Maneiro 5
  3. Losada, José Luís 6
  4. Casal, Claudio Alberto 34
  5. Ardá, Antonio 1
  1. 1 Department of Physical and Sport Education, University of A Coruña, Galicia, Spain
  2. 2 Universidad Europea de Madrid
    info

    Universidad Europea de Madrid

    Madrid, España

    ROR https://ror.org/04dp46240

  3. 3 Universitat de València
    info

    Universitat de València

    Valencia, España

    ROR https://ror.org/043nxc105

  4. 4 Department of Health Sciences, Isabel I University, Burgos, Spain
  5. 5 Universidade de Vigo
    info

    Universidade de Vigo

    Vigo, España

    ROR https://ror.org/05rdf8595

  6. 6 Universitat de Barcelona
    info

    Universitat de Barcelona

    Barcelona, España

    ROR https://ror.org/021018s57

Revista:
Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology

ISSN: 1754-3371 1754-338X

Año de publicación: 2024

Volumen: 42

Número: 1

Páginas: 11-20

Tipo: Artículo

DOI: 10.1177/17543371241254602 GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology

Resumen

The technical−tactical performance of women’s football has improved markedly in recent years. Despite this improvement, there are still differences between men’s football and women’s football. The objectives of this study were to know the technical and tactical key performance indicators (KPIs) that differentiate elite men’s and women’s football teams as well as to determine which statistical techniques demonstrate superior classification ability and interpretability in football terms. For this purpose, 768 matches corresponding to the latest editions of the UEFA Champions League, UEFA Euro and FIFA World Cup for men and women were analyzed. First, the differences at the bivariate level were analyzed using student’s t-test for independent sample (p < 0.05) for the male and female teams. Secondly, three data mining classification algorithms were applied: (i) Artificial Neural Network (ANN), (ii) Binary Logistic Regression, and (iii) Decision Tree. Significant differences were found between men’s football and women’s football in variables related to technical elements such as lost balls (ES = 1.19), ball recoveries (ES = 1.00), and accurate passes (ES = 0.97), as well as regulatory aspects like fouls (ES = 0.59), successful tackles (ES = 0.46), and yellow cards (0.45). On the other hand, the classification models presented excellent or good predictive capability [Range AUC 0.774−0.982], with very small differences between the ANN’s and logistic regression models. This result justifies the use of simpler models as the linear regression model to understand the differences between men’s and women’s football. Moreover, the observed differences may offer insights for future efforts aimed at enhancing the performance of women’s football.

Referencias bibliográficas

  • 10.1111/sms.13681
  • 10.2478/hukin-2021-0072
  • 10.1080/17430437.2022.2088358
  • Lago I, (2021), Int Rev Sociol Sport, 57, pp. 1
  • 10.1108/SBM-09-2017-0048
  • 10.1080/24733938.2020.1868560
  • 10.1080/24748668.2022.2101837
  • 10.1371/journal.pone.0268334
  • 10.3390/su13116379
  • 10.1111/sms.14206
  • 10.1016/j.humov.2013.07.024
  • Casal CA, (2021), J Hum Sport Exerc, 16, pp. 37
  • 10.1038/s41598-021-90264-w
  • 10.1371/journal.pone.0255407
  • 10.1371/journal.pone.0212549
  • 10.3389/fpsyg.2019.00223
  • 10.1111/j.1600-0838.2008.00861.x
  • 10.1111/sms.12860
  • de Jong LMS, (2019), PLoS One, 15, pp. e0240992, 10.1371/journal.pone.0240992
  • 10.5114/biolsport.2023.112970
  • 10.1177/1754337122113362
  • 10.1145/3105576
  • Inan T, (2021), J Hum Sport Exerc, 16, pp. 942
  • 10.1080/02640414.2020.1834689
  • Andersen TB, (2016), Int J Sports Med, 31, pp. 966
  • Bozzini BN, (2020), J Strength Cond, 34, pp. 3364
  • 10.1111/sms.13878
  • 10.1080/24748668.2020.1809320
  • James G, Witten D, Hastie J, et al. An introduction to statistical learning with application in R. 2nd ed. New York, NY: Springer, 2021, p.129.
  • 10.1007/978-3-030-03499-3
  • 10.1123/ijspp.1.1.50
  • Aryadoust V, Goh CCM. Predicting listening item difficulty with language complexity measures: a comparative data mining study. CaMLA Working Papers. CaMLA.
  • IBM. Neural networks. Multilayer perceptron. https://www.ibm.com/docs/en/spss−statistics/29.0.0?topic=networks−multilayer−perceptron (2023, accessed 5 July 2023).
  • 10.3390/math8101741
  • 10.1177/1747954120942051
  • 10.1080/02640414.2012.727455
  • 10.1080/24733938.2020.1722319
  • 10.1177/1754337113493083
  • 10.47197/retos.v43i0.88203
  • 10.3390/sports10040050