Sport Performance Analytics: Bridging Data Science and Decision-Making in Training and Competition

The field of sports science is increasingly shaped by the integration of data science, artificial intelligence (AI), wearable technology, video analytics, and performance monitoring systems. These tools are transforming how athletes train, compete, and recover by offering unprecedented insights into movement patterns, physiological states, and tactical strategies. Despite the rapid adoption of analytics and AI in high-performance environments, challenges remain in translating complex data into actionable insights that effectively inform coaching and performance decisions. Current research highlights the need for models that not only describe performance but also predict outcomes, assess risk, and guide individualized training adaptations. However, many of these systems are still evolving, with gaps in validity, interpretability, and practical integration into the daily workflow of sport practitioners.This Research Topic aims to advance the development and application of intelligent, data-driven methods for improving decision making in sport training and competition. Specifically, it seeks contributions that build bridges between the computational sciences and the practical demands of sports performance contexts. The goal is to highlight innovations that empower coaches, athletes, and support teams to make evidence-based decisions about training loads, tactical choices, and return-to-play protocols. This includes exploring data integration frameworks, algorithmic transparency, and the transfer of scientific findings to real-world practice. By bringing together multidisciplinary expertise, the Research Topic aspires to promote strategies that enhance both athletic development and competitive advantage.To gather further insights into the use of AI and data analytics for decision making in sport, we welcome articles addressing, but not limited to, the following themes:Performance prediction and optimization modelsTactical and match analysis through machine learning and computer visionWorkload monitoring, fatigue management, and recovery analyticsMovement assessment using wearable and sensor-based technologiesInjury prevention, risk profiling, and return-to-play analyticsTalent identification using multi-source data approachesCoach–athlete communication and feedback systems supported by technologyEthical considerations and data governance in sport analyticsAppendix – Article types: Original research, reviews, methodological papers, and applied case studies. Topic editors: Yumeng Li, Shuqi Zhang Source: https://www.frontiersin.org/research-topics/82062/sport-performance-analytics-bridging-data-science-and-decision-making-in-training-and-competition