Projects

Selected research and applied projects. Choose a project to read the full report or explore the work.

Screen Machine: Pre-Snap Play Prediction in the NFL

Undergraduate research at Carnegie Mellon using NFL player-tracking data to predict screen passes, their direction, and the intended receiver group before the snap.

ABS Challenge Likelihood

MLB

Baseball

A project modeling whether a pitch will be challenged, which team will challenge, and whether the call will be overturned, using R and XGBoost.

What Makes a Good Shot? Predicting NBA Shot Make Probability

NBA

Basketball

A project estimating NBA shot make probability from shot location, defender proximity, movement, and game context, with season-based validation and calibration checks.

Court IQ

An iOS app for coaches to design drills, track player statistics, and analyze performance trends, built with Swift, Firebase, and external APIs.

Ego-Motion Estimation & BEV Mapping

Python

OpenCV

NumPy

Estimated a vehicle’s 3D trajectory and built bird’s-eye-view maps from stereo video and RGB-D point clouds using Python, NumPy, and OpenCV.

March Madness Bracket Predictor

NCAAB

Basketball

An ensemble of XGBoost and logistic regression models predicting NCAA tournament outcomes using advanced team metrics and historical matchups.

NFL Analytics Suite

NFL

Football

Models and visualizations of fourth-down decisions, rushing and passing yards over expected, and team performance across four NFL seasons.