I've built decision-support tools for Denver Public Schools and University of Colorado Denver research, turning real-world data into actionable analysis. My work spans statistical modeling, predictive analytics, optimization, graph algorithms, and geospatial accessibility.
For Denver Public Schools, I built an attendance and student performance dashboard using four years of data from more than 2,000 students. I developed regression and Bayesian models that predicted student scores with approximately 78% accuracy and translated findings into visual summaries and administrative recommendations.
At the University of Colorado Denver, I developed a scalable Python framework for multimodal transit accessibility across a network of more than 2.3 million graph nodes. It combines GTFS data, pedestrian routing, RAPTOR, Dijkstra's algorithm, reverse accessibility analysis, Monte Carlo scenarios, and isochrone generation.
I'm an Applied Mathematics M.S. graduate who communicates complex quantitative ideas clearly to technical and nontechnical audiences. I use Python, R, SQL, Stan, Tableau, and statistical methods to build reliable models, pipelines, dashboards, and analyses.
