This summer, I competed in the SMT Data Challenge, leveraging player and ball tracking data to model the underlying thresholds behind a third base coach's decision to send a runner home. Using a logistic regression framework, I evaluated key decision factors, including how a coach’s physical positioning influences the call to send a runner. To address the challenge prompt, I translated these findings into a Live Send Probability Table, demonstrating how real-time analytics can directly enhance the fan experience in a stadium.
For my final project in Applied Statistical Modeling, my partner and I decided to examine how well betting markets have predicted the result of MLB games, and in particular, home field advantage. Through data analysis in RStudio, we were able to find very telling results about implied probabilities of MLB games.