I'm an economist turned data scientist who spent 12 years building a million-dollar coffee business while earning my MA in Economics. Now I focus on machine learning and statistical modeling, with a particular interest in causal inference and healthcare analytics.

Economics taught me that stories are rarely simple and every decision has hidden costs. Data science lets me quantify these trade-offs and uncover the costs that surface-level analysis might miss. At Veterans United Home Loans, I developed delinquency prediction models for multi-billion dollar mortgage portfolios that replaced grid-based systems with continuous modeling. The old approach used discrete FICO score bins where a loan with a 759 score was valued identically to one with a 740 score, but a 760 score received a substantial jump in valuation despite minimal marginal risk difference. My continuous models revealed the hidden cost of this approach: suboptimal keep-versus-sell decisions that left money on the table when meeting portfolio retention targets.

My self-directed work applies this same economic reasoning to broader problems. For coursework, I built a comprehensive benefit-cost analysis for the City of Kirkwood's fleet electrification policy, demonstrating how economic trade-offs play out in municipal decision-making. On my own time, I created an open-source Python package that unifies gradient boosting algorithms with automated hyperparameter optimization and system resource detection, filling a gap for analysts working on local machines without dedicated infrastructure teams. These projects reflect my belief that good analysis requires understanding both the technical tools and the underlying questions they're meant to answer.

I'm drawn to problems where insights into causality can complement and yield as much value as predicting outcomes. I want to know not only what works, but why it works. This perspective becomes especially valuable when the stakes are high and getting the causal relationships right makes a real difference.