Leakage-free weekly fantasy projections for QB/RB/WR/TE built end-to-end in PySpark over nine seasons of nflverse data.
A hybrid collaborative-filtering recommender that turns your Spotify listening history into personalized artist recommendations, deployed as a live Streamlit web app.
Group project predicting monthly highway-rail grade crossing accidents from weather conditions, built as a fully reproducible DVC pipeline over 50 years of FRA and NOAA data.
Forecasting housing affordability across Pennsylvania’s Philadelphia, Pittsburgh, and Harrisburg metros through 2028 using ARIMA and XGBoost.
Predicting Spotify song popularity across pop, rock, and jazz by comparing eight regression and tree-based models.
Third-place finish predicting premium seating pricing tiers at the Milwaukee Bucks Business Analytics Hackathon.