Data Analyst / Data Scientist
I am a data sense-maker who specializes in forecasting, visualization, and data storytelling. My work ranges from helping a local bakery stabilize supplier pricing and reduce procurement risk to building dashboards at Coyote Capital Management that guide sector-level investment decisions. I enjoy modeling and analytics as much as communicating insights and teaching non-technical teams to use data for better business performance.
I am set to graduate with an M.S. in Business Analytics from the University of South Dakota and am seeking data analyst or data scientist roles where I can turn complex data into practical decisions that drive measurable results.
Toolkit: SQL, Python, R, Power BI, Excel, SAS, Spark, Tableau
These projects were created in collaboration with real organizations or student groups. The focus was on building solutions that could be applied and shared with others.
Forecasted egg price fluctuations for Mister Smith's Bakery to secure cost-effective supplier contracts and avoid price shocks for customers.
Growth analytics pipeline using DuckDB and SQLMesh (SCD2 dims + subscription-change fact) with hourly cron for upgrade, churn, and revenue insights.
Engineered a centralized reservation tracking system for Canyon Ranch resorts, improving service responsiveness and replacing outdated data systems.
Built a machine learning model to predict delivery times based on traffic and order flow, helping DoorDash improve ETA accuracy and customer satisfaction.
Scraped and structured NCAA game data into a relational database, then developed an interactive dashboard to optimize referee scheduling and performance insights.
End-to-end customer churn analysis combining descriptive insights and predictive modeling (XGBoost, Random Forest) to identify at-risk subscribers and optimize retention strategy for a music streaming service.
These are self-initiated projects where I explored new tools, models, or ideas. They reflect my curiosity and commitment to continuous growth.
Modeled 4th down plays in SAS to guide better game-time decisions.
Predicted used car prices with regression based on year, mileage, and engine specs.
Analyzed passenger claims to find trends in baggage handling incidents.
Segmented customers by RFM metrics to guide loyalty strategies.
Built Solver-based model to reduce production cost while meeting nutrition targets.