Designed a robust SQL data model and built a self-serve Tableau dashboard to track customer demographics, journey, and KPIs, enabling the diagnosis of customer drop-off points.
Performed in-depth EDA and feature engineering to identify key ridership patterns and developed a GRU-based deep learning model in PyTorch to forecast daily Citi Bike demand. This project successfully captured complex temporal and weather-driven dependencies to provide actionable insights for fleet rebalancing and operational planning.
Designed a NLP pipeline using NLTK and Scikit-learn to process and classify real-world disaster tweets from noisy social media data. Achieved 85.9% test accuracy, demonstrating a highly effective and reliable tool for filtering critical information for emergency response teams.
Developed a logistics optimization model for Walmart-style distribution networks across 3 states. Used geodesic clustering and TSP algorithms to design efficient delivery routes across 50+ stores. Reduced simulated travel distance by 23% through centroid-based routing and dynamic warehouse-to-store zoning.
Built an interactive Excel-based marketing analytics platform analyzing ad performance across U.S. regions. Identified top-performing channels and underperforming regions using pivot-based dashboards. Recommended region-specific ad optimizations, improving forecast accuracy and ROI tracking
GPA: 3.74/4.0
Relevant Coursework:
My inbox is always open for a good conversation about data science, building new projects, or potential collaborations. Let's get in touch!