CNLD Seminar with Amanda Glazer

Abstract: In this talk, I’ll present an overview of sports analytics, highlighting its history and recent advances. I’ll then introduce new, tractable methods for detecting changes in player performance metrics, applied to Major League Baseball (MLB) batting and pitching data from the 2023 and 2024 seasons. The proposed changepoint detection algorithm combines a likelihood-based approach with split- sample inference to control false positives. I demonstrate its utility across several baseball applications, including detecting changes in batter plate-discipline metrics (e.g., chase and whiff rate), identifying fastball velocity shifts in pitchers, and validating velocity changepoints against a curated ground-truth dataset of pitchers who transitioned from relief to starting roles. The method flags meaningful changes in 91% of these ground-truth cases and reveals that, for some metrics, more  than 60% of detected changes occur in-season.