Projects centered on data pipelines, machine learning models, and decision-driven analytics.
🍽 NYC Dining Safety Prediction (Machine Learning)
Description:
A machine learning project that predicts NYC restaurant health inspection grades (A / B / C) using inspection history, NYC 311 complaints, census data, and neighborhood-level socioeconomic indicators.
The modeling strategy emphasizes high recall for Grade C (high-risk) restaurants to support proactive public health inspection planning.
📊 Customer Targeting
Description:
Developed an RFM segmentation and clustering engine using Python and scikit-learn to identify high-value customers for targeted campaigns. Integrated A/B testing to validate marketing performance lifts.
🛍️ Omnichannel Expansion
Description:
Built a dashboard to track user engagement across e-commerce and retail store touchpoints using Tableau + SQL. Supported strategy for physical expansion based on regional online-to-offline conversion rates.