Key result
A linear logistic regression model achieved the best overall classification performance (mean macro-F1 = 0.729) compared to ensemble and kernel-based methods.
Why the study?
Studies were needed to analyze the performance of professional soccer players in relation to their playing position using machine learning models.
Machine learning models, particularly logistic regression, can effectively classify professional soccer player performance levels, demonstrating that performance structures differ substantially by playing position.
Answers are grounded in this paper and cite their sources.
Position-specific analysis may guide soccer training; hypothesis-generating and requires validation before changing practice.
Background. Recent advances in data systematization have enabled the development of machine learning models to evaluate performance in elite sports; however, studies are needed to analyze the performance of professional players in relation to their playing position. Objective. To analyze the performance of professional soccer players who competed between 2017 and 2024 by applying a multilevel classification approach that integrates different machine learning algorithms. Materials and Methods. We analyzed 9088 player-seasons from professional players during the 2017–2024 seasons. These data were extracted from standardized databases on sports performance analysis belonging to the following leagues: LaLiga (Spain), Premier League (England), Bundesliga (Germany), Serie A (Italy), and Ligue 1 (France). The final sample, distributed by performance level, was as follows: elite players (n = 1818; 20%), mid-level players (n = 2727; 30%), and low-level players (n = 4543; 50%). The average age of the players analyzed was 26.1 ± 4.0 years, distributed across three outfield playing positions: center backs (CB), central midfielders (CM), and strikers (ST); goalkeepers were excluded because the dataset contains no goalkeeper-specific performance metrics. Results. Under a leakage-controlled protocol (the label-defining indicators were excluded from the predictors and the train/test split preceded all preprocessing), a linear model (logistic regression) achieved the best overall performance (mean macro-F1 = 0.729), ahead of ensemble and kernel-based methods; this indicates that, once target leakage is removed, the classification does not require non-linear models. Strikers (ST) were the most separable position (best macro-F1 = 0.818, area under the receiver operating characteristic curve [AUC-ROC] = 0.948) and center backs (CB) the most difficult (macro-F1 = 0.602, AUC-ROC = 0.791), with midfielders (CM) intermediate (macro-F1 = 0.770, AUC-ROC = 0.916). Conclusions. The results confirmed that performance structures differ substantially depending on the position in the field, supporting the use of position-specific analytical strategies. In this context, the combination of position-stratified dimensionality reduction, handling of imbalance, and explainable artificial intelligence allowed for the identification of interpretable performance patterns associated with the profiles of elite, mid-level, and low-level players.
No takes yet. Share an insight, caveat, or question.
Patiño et al. (2026) studied Professional soccer performance (n=9,088). Logistic regression model vs. Ensemble and kernel-based methods was evaluated on Overall classification performance (mean macro-F1). A linear logistic regression model achieved the best overall classification performance (mean macro-F1 = 0.729) compared to ensemble and kernel-based methods.
Synapse has enriched 10 related papers. Consider them for comparative context: