Abstract :

Injuries in professional soccer significantly affect player performance, team success, and financial costs. Traditional injury prevention methods rely on manual observation and historical experience, which may not effectively predict injury risks. This project proposes an Injury Risk Prediction System for soccer players using Machine Learning techniques. The system analyses player data such as training load, match intensity, physical fitness, and previous injury history. Machine learning models identify patterns associated with injury occurrence. The proposed approach enables early identification of high-risk players. Coaches and medical staff can use these insights to adjust training plans. Automation improves prediction accuracy and reduces injury incidence. The system supports data-driven decision-making in sports science. It enhances player health management and team performance. This project demonstrates the application of machine learning in sports analytics.