Player Performance Modeling & Applied Analytics in Sport

3 credits

This course examines the application of advanced statistical modeling and computational analytics to player performance evaluation, injury risk prediction, player development, and strategic decision-making across multiple sports. Students will build and evaluate predictive and unsupervised learning models using real-world sport datasets, integrating feature engineering, model validation, clustering, simulation, and performance comparison techniques.Emphasis is placed on both technical execution and decision translation. Students will construct logistic regression injury models, develop player projection systems, cluster player archetypes, perform cross-validation, compare model performance (AUC, RMSE), and conduct Monte Carlo simulations to quantify performance variability and risk.Beyond model construction, students will learn to translate complex analytical findings into actionable recommendations for coaching staff, performance directors, and front office leadership. By the end of the course, students will be able to design, evaluate, and defend performance models within applied sport environments.This course requires prior coursework in statistics and programming (Python or R).