Sport League

Research on sports leagues is increasingly focused on leveraging data-driven methods to improve decision-making and understanding of game dynamics. Current studies employ machine learning techniques, such as hidden Markov models, XGBoost, LightGBM, and neural networks, to predict match outcomes, analyze player performance, and optimize league scheduling, particularly in scenarios like shortened seasons. This work has implications for team management (e.g., player scouting, strategic planning), fan engagement (e.g., enhanced game analysis tools), and the development of more sophisticated predictive models across various sports and e-sports.