EUVIMEDOtkrijte EUVIMED
Open access · CC BY 4.0

Performance Profiles in Youth Basketball Across Different Score Contexts: An Unsupervised Machine Learning Analysis

Dimitrios Pantazis iD, Christos Kokkotis, Alexandra Avloniti iD, Theodoros Stampoulis iD, Panagiotis Foteinakis iD, Panagiotis Aggelakis iD, Dimitrios Balampanos iD, Maria Protopapa iD, Alexandros Dendrinos, Konstantinos Margonis iD, Nikolaos Zaras iD, Georgios Pafis and 3 more

Journal of Functional Morphology and Kinesiology · 2026-07-21 · 11 (3) · 282

DOI: 10.3390/jfmk11030282 ↗

At a glance

Journal article in Journal of Functional Morphology and Kinesiology, published online on 2026-07-21. Written by Dimitrios Pantazis and 14 co-authors. Institution: Department of Physical Education and Sport Science, School of Physical Education, Sport Science and Occupational Therapy, Democritus University of Th…. 68 references. The full text is freely available (open access, CC BY 4.0). Funded by: European Union - NextGenerationEU through the Recovery and Resilience Facility (RRF) for the period 2022-2025, with the contribution of the National Public Inv…, European Union–NextGenerationEU, National Public Investment Programme.

SažetakSubjectsBibliografski podaciCiteRelated studies

Abstract (original language)

Objectives

The analysis of basketball performance has increasingly incorporated advanced analytics and machine learning methods to better understand the factors that influence offensive efficiency and match dynamics. The present study aimed to identify performance profiles in basketball using unsupervised machine learning techniques and to examine the physical load and performance indicators that differentiate these profiles.

Methods

Team-quarter observations from the Final 8 phase of the Greek U16 Basketball Championship were stratified into quarters with large score differences and quarters with small score differences according to the quarter-specific score differential and the sample median of 5 points. K-means clustering was applied separately to each dataset to identify latent performance patterns. Candidate solutions were evaluated using the Elbow method, Silhouette coefficient, Calinski–Harabasz Index, and Davies–Bouldin Index. Based on their combined interpretation, together with considerations of parsimony and practical interpretability, two-cluster solutions were retained for both datasets. Cluster stability was assessed using the Adjusted Rand Index (ARI), while t-distributed stochastic neighbor embedding (t-SNE) was used exclusively for visualization of the identified clusters.

Results

Welch’s independent-samples t-tests with Benjamini–Hochberg false discovery rate (FDR) correction identified significant differences between clusters across several external load variables, including jump load, total distance covered, accumulated acceleration load, and distance covered in different speed zones (pFDR < 0.001). Clusters characterized by higher movement intensity also exhibited higher values for basketball performance and offensive-efficiency indicators. Although higher-performance clusters showed numerically higher winning proportions in both contexts (large score differences: 70.0% vs. 45.7%; small score differences: 56.7% vs. 40.6%), chi-square analyses indicated that cluster membership was not significantly associated with quarter outcomes.

Conclusions

Overall, the findings suggest that performance profiles in basketball are primarily differentiated by external-load characteristics, particularly movement intensity, and offensive-performance indicators, highlighting the importance of integrating both physical and technical performance indicators in basketball performance analysis.

Subjects

Author keywords

basketball performance analysisk-means clusteringmovement intensityoffensive performancephysical loadunsupervised machine learning

Authors and institutions

  • Department of Physical Education and Sport Science, School of Physical Education, Sport Science and Occupational Therapy, Democritus University of Thrace, 69100 Komotini, Greece.
  • Department of Occupational Therapy, School of Physical Education, Sport Science and Occupational Therapy, Democritus University of Thrace, 69100 Komotini, Greece.

ORCID profiles: Dimitrios Pantazis, Alexandra Avloniti, Theodoros Stampoulis, Panagiotis Foteinakis, Panagiotis Aggelakis, Dimitrios Balampanos, Maria Protopapa, Konstantinos Margonis, Nikolaos Zaras, Maria Michalopoulou, Athanasios Chatzinikolaou

Funding

  • European Union - NextGenerationEU through the Recovery and Resilience Facility (RRF) for the period 2022-2025, with the contribution of the National Public Inv…
  • European Union–NextGenerationEU
  • National Public Investment Programme

Cite

APA

Pantazis, D., Kokkotis, C., Avloniti, A., Stampoulis, T., Foteinakis, P., Aggelakis, P., Balampanos, D., Protopapa, M., Dendrinos, A., Margonis, K., Zaras, N., Pafis, G., Malliou, P., Michalopoulou, M., & Chatzinikolaou, A. (2026). Performance Profiles in Youth Basketball Across Different Score Contexts: An Unsupervised Machine Learning Analysis. Journal of Functional Morphology and Kinesiology, 11(3), 282. https://doi.org/10.3390/jfmk11030282

Vancouver

Pantazis D, Kokkotis C, Avloniti A, Stampoulis T, Foteinakis P, Aggelakis P, et al. Performance Profiles in Youth Basketball Across Different Score Contexts: An Unsupervised Machine Learning Analysis. Journal of Functional Morphology and Kinesiology. 2026;11(3):282. doi:10.3390/jfmk11030282

BibTeX
@article{Pantazis2026,
  author = {Pantazis, Dimitrios and Kokkotis, Christos and Avloniti, Alexandra and Stampoulis, Theodoros and Foteinakis, Panagiotis and Aggelakis, Panagiotis and Balampanos, Dimitrios and Protopapa, Maria and Dendrinos, Alexandros and Margonis, Konstantinos and Zaras, Nikolaos and Pafis, Georgios and Malliou, Paraskevi and Michalopoulou, Maria and Chatzinikolaou, Athanasios},
  title = {Performance Profiles in Youth Basketball Across Different Score Contexts: An Unsupervised Machine Learning Analysis},
  journal = {Journal of Functional Morphology and Kinesiology},
  year = {2026},
  volume = {11},
  number = {3},
  pages = {282},
  doi = {10.3390/jfmk11030282}
}
Start for free →