Lucius E. J. Bynum

Harvey Mudd College Mathematics 2017

mugshot
Thesis Proposal: From Partially Ranked Data to Fully Ranked Decisions: Prescriptive Analytics for Professional Basketball Data
Thesis Advisor: Prof. Susan E Martonosi
Second Reader: Prof. Michael E. Orrison
E-Mail: lbynum@math.hmc.edu

From Partially Ranked Data to Fully Ranked Decisions: Prescriptive Analytics for Professional Basketball Data

Sports analytics problems have become increasingly prominent in the past decade. Modern image processing capabilities allow coaching staff to easily capture detailed game-time statistics on their players, opponents, team configurations, and plays. The challenge is to turn that data into meaningful insights for team managers and coaches. This project aims to analyze play-by-play data from public sources such as NBA.com, ESPN.com, and basketball-reference.com. Using this data, we apply descriptive techniques rooted in the algebraic study of partially ranked data coupled with predictive techniques rooted in machine learning to identify powerful subsets of players and predict how they will perform against other teams. Predictive techniques are then overlaid with optimization heuristics to make coaching recommendations in real time.