Sports and Data

3 credits · Undergraduate

This course introduces undergraduates to data analytics and AI, using sports as the motivating application. Through real-world examples from professional sports, students will explore exploratory data analysis, regression, classification, clustering, dimensionality reduction, and neural networks. A major new emphasis this quarter is video analysis: students will work directly with game footage, learning how modern computer vision turns raw video into structured data through player and ball detection, multi-object tracking, pose estimation, and event recognition, and how the resulting tracking data supports analyses that box scores cannot. Weekly assignments and a final team project will develop students' skills in using Python-based tools for sports analytics, including video and tracking pipelines alongside conventional tabular workflows. The course features guest lectures from practitioners at Stanford sports as well as professional sports leagues. This quarter (Fall 2026) will feature close collaboration with Stanford Football and the SF 49ers, including guest lectures and potential course projects.