Datathletics: Diving into Data Analytics and Stanford Sports

Catalog description

Sophisticated data collection and analysis are now key to program success across many sports: Nearly all professional and national-level teams employ data scientists, and "datathletics" is becoming prevalent in college sports as well. This immersive seminar combines extensive hands-on data analytics with a first-hand peek into Stanford athletics. Class meetings roughly alternate between: (1) instruction in a variety of tools and techniques for analyzing and visualizing data; and (2) guest lectures by Stanford athletics coaches explaining how data is or could be used in their sport. Through regular problem sets, students bring each week's tools to bear on data related to the week's sport. One goal of the class is empowering students to perform compelling data analytics by mastering tools across a wide spectrum, including spreadsheets, the Tableau system for data preparation and visualization, Jupyter notebooks, relational databases and SQL, Python and many of its data-specific packages including Pandas, and machine learning. On the sports side, while the Stanford coaches may touch on many aspects of data collection and analysis, the main focus of this course is on using data for strategic decision-making rather than optimizing individual human performance. Prerequisites: No background in statistics or data analysis is needed, but basic programming and computing skills at the level of high school computer science or CS106A is expected. On the flip side, students with extensive experience in coding or data science may not be challenged by the technical aspects of the course.