Great Lakes Analytics in Sports Conference
Senior Data Scientist | STATS
Understanding Sport Through Player Tracking Data
By leveraging STATS' wealth of player tracking data and machine learning techniques, we are able to generate new analyses and insights into the game. By learning the appropriate representation of multi-agent tracking data, we are able to predict how teams and players move and behave in various situations. Finally, we look ahead to how tracking a player's pose provides an even more detailed and complete description of the game.
Jennifer Hobbs is a senior data scientist at STATS working on fine-grained prediction using basketball and soccer player-tracking data. She completed her undergraduate degree at Northwestern University majoring in integrated science, math, and physics, and earned her master's and PhD in physics and astronomy from Northwestern. Over the past two years at STATS, Jennifer has done work on all phases of the data science life cycle, transforming raw data into compelling technology products through data modeling and architecture, data pipeline design and management, machine learning and AI, and interactive visualization and prediction. In particular she has done work on personalized expected points models and team style analysis in basketball, and transition and formation analysis in soccer.
Follow STATS on Twitter
Watch a video of Jennifer's 2018 GLASC presentation
Back to Great Lakes Analytics in Sports Conference