Boom! Using Explosive Plays to Predict the Next Breakout Running Back
An award-winning sports analytics stacked-ensemble ML architecture that processes spatiotemporal data to predict breakout NFL running plays.
Machine Learning
Python
Project Overview
Presentation Type: Poster Presentation (Emory Center for AI Learning Research Showcase).
Technologies Used: Python, XGBoost, Multi-Layer Perceptron (MLPNN), Convolutional Neural Networks (CNN), Feature Engineering, Spatiotemporal Data Analysis.
Timeline: Jan 2025 – Present (Presented 2025).
My Role: Lead Sports Analytics Researcher.
Overview: Developed a sports analytics stacked-ensemble machine learning architecture to forecast explosive NFL runs. Engineered custom spatiotemporal features and trained base-level models (XGBoost, MLPNN, CNN) combined with a shallow XGBoost meta-learner to maximize predictive accuracy for player evaluation.
Honors / Recognition: Best Poster Award & Emory AI X.perience Fellowship.
How to Access: Poster / Slides: https://drive.google.com/file/d/1ZsZ-4FqmgUCKGSGVa4Tl-hKAtGJQa7p1/view?usp=sharing