<![CDATA[Purpose: Football has increasingly become a multidisciplinary field that integrates not only physical and tactical elements but also technological advancements to enhance decision-making. One of the prominent developments in this domain is the application of machine learning (ML) techniques to analyze match-related data, assess player performance, and optimize team strategies. This study aims to conduct a systematic literature review of contemporary research that employs machine learning algorithms within the context of football. Materials and Methods: A total of 50 scientific articles were initially retrieved from various reputable databases. Following a rigorous screening and eligibility assessment, 30 articles were selected for detailed analysis. Result: These studies employ diverse machine learning approaches, including Support Vector Machines (SVMs), Random Forests, XGBoost, Deep Learning, and clustering methods, for a wide range of purposes, such as match outcome prediction, player performance evaluation, injury detection, and playing position classification. The findings of this review underscore the potential of machine learning to contribute significantly to data-driven decision-making in football, providing valuable insights for coaches, performance analysts, and club management. Conclusion: Furthermore, this study identifies key challenges that remain, including data quality, data availability, and the interpretability of complex models. This review will serve as a critical reference for researchers and practitioners advancing intelligent technologies in sports, with particular emphasis on football.]]>
