A0265
Title: College football volatility: A Bayesian state-space model of the transfer portal and NIL impact
Authors: Ronald Yurko - Carnegie Mellon University (United States) [presenting]
Abstract: The landscape of American college football has changed dramatically in recent years with conference realignment, increased usage of the transfer portal, and the seismic legal ruling regarding athletes' name, image, and likeness (NIL). A Bayesian state-space model is used to capture the impact of transfers and NIL on the volatility of team strengths over time. Specifically, the classic autoregressive process for team strength is extended by modeling the between-season innovation variance as a function of incoming transfers and NIL rule changes. This approach enables predicting greater variance for team strengths in an upcoming season based on roster changes. Results from the playoff era (2014-2024) reveal variation between schools that have embraced the volatility of transfers (e.g., Deion Sanders at Colorado) and those who have been reluctant to change (e.g., Iowa and Clemson). Variability is explored in the effects between different positions of incoming transfers, and the predictive performance of the novel approach is compared with simpler state-space models.
