Abstract
The aim of this research is to shed light on the complex interactions between player workload, traits, match-related factors, football performance, and injuries in the English Premier League. Using a range of statistical and machine learning techniques, this study analyzed a comprehensive dataset that included variables such as player workload, personal traits, and match statistics. The dataset comprises information on 532 players across 20 football clubs for the 2020–2021 English Premier League season. Key findings suggest that data, age, average minutes played per game, and club affiliations are significant indicators of both performance and injury incidence. The most effective model for predicting performance was Ridge Regression, whereas Extreme Gradient Boosting (XGBoost) was superior for predicting injuries. These insights are invaluable for data-driven decision-making in sports science and football teams, aiding in injury prevention and performance enhancement. The study’s methodology and results have broad applications, extending beyond football to impact other areas of sports analytics and contributing to a flexible framework designed to enhance individual performance and fitness.
Original language | English |
---|---|
Article number | 7217 |
Number of pages | 32 |
Journal | Applied Sciences |
Volume | 14 |
Issue number | 16 |
Early online date | 16 Aug 2024 |
DOIs | |
Publication status | Published - Aug 2024 |
Bibliographical note
Copyright © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms andconditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)
Keywords
- football analytics
- injury occurrence analysis
- machine learning in sports
- predictive modelling
- sports data analysis