Optimizing football analytics: Dimensionality reduction meets machine learning for offensive and defensive player profiling

@article{yanezsepulveda2026optimizing,
  title = {{Optimizing football analytics: Dimensionality reduction meets machine learning for offensive and defensive player profiling}},
  author = {Rodrigo Yáñez-Sepúlveda and Aldo Vásquez-Bonilla and Rodrigo Olivares and Pablo Olivares and Guillermo Cortés-Roco and Eduardo Guzmán-Muñoz and Marcelo Tuesta and Jorge Olivares-Arancibia and Boryi A. Becerra-Patiño and Juan David Paucar-Uribe and Diego Andrés Rada-Perdigón and Exal Garcia-Carrillo and Tomás Rivera-Kofler and Vicente Javier Clemente-Suárez and José Francisco López-Gil},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0353239},
  url = {https://doi.org/10.1371/journal.pone.0353239},
  note = {CC BY 4.0},
}

TY  - JOUR
TI  - Optimizing football analytics: Dimensionality reduction meets machine learning for offensive and defensive player profiling
AU  - Rodrigo Yáñez-Sepúlveda
AU  - Aldo Vásquez-Bonilla
AU  - Rodrigo Olivares
AU  - Pablo Olivares
AU  - Guillermo Cortés-Roco
AU  - Eduardo Guzmán-Muñoz
AU  - Marcelo Tuesta
AU  - Jorge Olivares-Arancibia
AU  - Boryi A. Becerra-Patiño
AU  - Juan David Paucar-Uribe
AU  - Diego Andrés Rada-Perdigón
AU  - Exal Garcia-Carrillo
AU  - Tomás Rivera-Kofler
AU  - Vicente Javier Clemente-Suárez
AU  - José Francisco López-Gil
PY  - 2026
DA  - 2026/09/09
JO  - PLOS One
DO  - 10.1371/journal.pone.0353239
UR  - https://doi.org/10.1371/journal.pone.0353239
AB  - Background: This study focuses on the quantitative analysis of football players’ performance based on a set of performance data. Objective: The objective of this study was to develop a multivariate analytical model to identify, quantify, and predict the most relevant factors that determine the offensive and defensive profiles of professional football players, thereby optimizing functional segmentation, performance analysis, and decision-making processes in the contexts of scouting and data-based tactical planning. Materials and methods: A dataset was compiled through automated extraction (web scraping) via the Python programming language and its specialized libraries. The full dataset comprised 2,689 player–league records corresponding to 2,530 unique players from Europe’s five major UEFA-affiliated national leagues during the 2022–2023 season (159 players who transferred between two leagues mid-season contributed one record per league, 2,530 + 159 = 2,689). After applying a minimum-eligibility filter of >450 minutes played to ensure stable per-90 metrics, 1,624 player–league records (1,620 unique players) were retained for the modeling workflow. Dimensionality reduction techniques (PCA) and explainable machine learning (Shapley Additive exPlanations [SHAP]) with predictive modeling were applied. Eight algorithms were trained and compared to predict PC1 Offensive and PC1 Defensive. Results: The First Offensive Principal Component (PC1 Offensive) synthesizes actions that generate scoring opportunities, such as actions prior to shots (SCA_p90, 13.3%), progressive receptions (RecProg_p90, 13.0%) and total shots (Shots_p90, 12.7%). The first-defensive principal component (PC1 Defensive) highlights tackles (Tkl_p90, 19.1%), blocks (15.6%) and interceptions (15.6%). Conclusions: Finally, the inclusion of SHAP allows for an in-depth interpretation of the models, identifying the key statistical factors that influence players’ offensive and defensive contributions, which is valuable for scouting, tactical analysis and player development.
SN  - 1932-6203
ER  -