Welcome to Mike’s data science portfolio! Below are selected projects that showcase my work in applied machine learning, behavioral analytics, geospatial modeling, and stakeholder-driven insights. ...

In collaboration with non-profit organizations, I’ve developed predictive models and interactive dashboards to support national campaign strategy and local outreach optimization. This project spans...

Clustering can be a powerful tool for grouping individuals based on their political perceptions—and by extension, their likelihood to shift how they vote. Using HDBSCAN clustering on individual Ca...

InsightAtlas – a flexible, mobile-friendly dashboard for exploring and sharing geographic insights through data (see live demo). Built to support collaboration with non-partisan NGOs, enabling ...

A modular, automated machine learning pipeline for multi-component feature extraction and classification. Rigorously A/B tested Adopted by 8+ project initiatives over competing tools Contri...

A specialized ridge detector for high-dimensional datasets, crucial for segmenting complex patterns. Contributing to 4 peer-reviewed publications (80 citations) to date, with additional studies...

Flight Price Model - an XGBoost-based flight price forecasting model. Achieving 92% accuracy, using feature selection and tuning optimization. For more, please see: GitHub