This study determined the contributors to soccer technical skill in grassroots youth soccer players using a machine learning approach. One hundred and sixty two boys aged 7-14 (Mean ± SD = 10.5 ± 2.1) years, who were regularly engaged in grassroots soccer undertook assessments of anthropometry and maturity offset (the time from age at peak height velocity (APHV)), Fundamental Movement skills (FMS), perceived physical competence, and physical fitness and technical soccer skill using the university of Ghent (UGent) dribbling test. Coaches rated player’s overall soccer skill for their age. Statistical analysis was undertaken, using machine learning models to predict technical skill from the other variables. A stepwise recursive feature elimination with a 5-fold cross-validation (RFECV) method was used to eliminate the worst performing features and both L1 and L2 regularisation were evaluated during the process. Five models (linear, ridge, lasso, random forest, boosted trees) were then used in a heuristic approach using a small subset of suitable algorithms to achieve a reasonable level of accuracy within a reasonable time frame) to make predictions and compare them to a test set to understand the predictive capabilities of the models. Results from the machine learning analysis indicated that total FMS score (0-50) was the most important feature in predicting technical soccer skill followed by coach rating of child skill for their age, years playing experience and APHV. Using a random forest, technical skill could be predicted with 99% accuracy in boys who play grassroots soccer, with FMS being the most important contributor.
|Journal||International Journal of Sports Science and Coaching|
|Publication status||Accepted/In press - 1 Sept 2023|
- Motor Skill
- Talent Identification
- Motor Competence
- Machine learning