No items found.

Using Machine Learning to Describe How Players Impact the Game in the MLB - An Open Source Workshop

No items found.
About This Event

This session will introduce participants to concepts, techniques, and relevant work from two growing domains of machine learning – Natural Language Processing (NLP) and Computer Vision (CV) – through the lens of open-source research done by Research Paper Competition participant, Connor Heaton. Connor’s work suggests a new way in which the game of baseball can be analyzed, described, and interrogated. Historically, baseball enthusiasts have used relatively simple counting- and rate-statistics to describe a given player, game, or team. While informative, Connor believes more can be gained by analyzing the sequence of in-game events in which players participate in context – how earned runs were surrendered and the manner in which innings were pitched, for example. Given the context of Connor’s work and the relevant knowledge of NLP and CV, participants will learn how these techniques can be adapted to derive rich representations from a sequence of pitches (events) in the MLB.

Attendees should come with Python installed and downloaded prior to the workshop. The dataset and required dependencies can be found in the git repository:

March 5, 2022
2:30 pm
3:30 pm
See Full Schedule
Dropbox Access Link