EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting special forces dropout via explainable machine learning

Rik Huijzer iD, Peter de Jonge, Frank J Blaauw, Maurits Baatenburg de Jong, Age de Wit, Ruud J R Den Hartigh

European Journal of Sport Science · 2024-11 · 24 (11) · 1564-1572

DOI: 10.1002/ejsc.12162 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Sport Science, online erschienen am 24.09.2024. Verfasst von Rik Huijzer und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Behavioural and Social Sciences, Department of Developmental Psychology, University of Groningen, Groningen, the Netherlands. Hauptthemen laut MEDLINE: Machine Learning, Military Personnel. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerie van Defensie.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Selecting the right individuals for a sports team, organization, or military unit has a large influence on the achievements of the organization. However, the approaches commonly used for selection are either not reporting predictive performance or not explainable (i.e., black box models). In the present study, we introduce a novel approach to selection research, using various machine learning models. We examined 274 special forces recruits, of whom 196 dropped out, who performed a set of physical and psychological tests. On this data, we compared four machine learning models on their predictive performance, explainability, and stability. We found that a stable rule‐based (SIRUS) model was most suitable for classifying dropouts from the special forces selection program. With an averaged area under the curve score of 0.70, this model had good predictive performance, while remaining explainable and stable. Furthermore, we found that both physical and psychological variables were related to dropout. More specifically, a higher score on the 2800 m time, need for connectedness, and skin folds was most strongly associated with dropping out. We discuss how researchers and practitioners can benefit from these insights in sport and performance contexts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningMilitary PersonnelHumansMaleYoung AdultPersonnel SelectionAdult

Stichwörter der Autor:innen

SIRUS modelassessmentmilitary selectionperformanceperformance prediction

Autor:innen und Institutionen

  • Faculty of Behavioural and Social Sciences, Department of Developmental Psychology, University of Groningen, Groningen, the Netherlands.
  • Research and Innovation, Researchable BV, Assen, the Netherlands.
  • Ministry of Defence, Den Haag, the Netherlands.

ORCID-Profile: Rik Huijzer

Förderung

  • Ministerie van Defensie

Zitieren

APA

Huijzer, R., de Jonge, P., Blaauw, F. J., Baatenburg de Jong, M., de Wit, A., & Den Hartigh, R. J. R. (2024). Predicting special forces dropout via explainable machine learning. European Journal of Sport Science, 24(11), 1564-1572. https://doi.org/10.1002/ejsc.12162

Vancouver

Huijzer R, de Jonge P, Blaauw FJ, Baatenburg de Jong M, de Wit A, Den Hartigh RJR. Predicting special forces dropout via explainable machine learning. European Journal of Sport Science. 2024;24(11):1564-1572. doi:10.1002/ejsc.12162

BibTeX
@article{Huijzer2024,
  author = {Huijzer, Rik and de Jonge, Peter and Blaauw, Frank J and Baatenburg de Jong, Maurits and de Wit, Age and Den Hartigh, Ruud J R},
  title = {Predicting special forces dropout via explainable machine learning},
  journal = {European Journal of Sport Science},
  year = {2024},
  volume = {24},
  number = {11},
  pages = {1564--1572},
  doi = {10.1002/ejsc.12162}
}
Kostenlos starten →