Maintaining and updating team’s database in Python and R containing report templates and machine learning modelsBuilding and running postgame statistical reports for coaches to analyze such as batter plots and umpire reportsCreating scripts for tasks such as converting data from Hawkeye to Trackman format and generating formulas for scouting reports

Developing semantic embeddings for satellite images of US counties with cancer cases using the Clay Foundation ModelAnalyzing predictive models, including Random Forest and LASSO, on embeddings to determine geographic patterns in cancer rates

Built robust data pipelines to support a price-tracking product identifying optimal purchasing times based on historical dataImplemented data scrapers with API integrations to extract data from multiple sources and applied SQL techniques for refinementDeveloped shell scripts to streamline data integration into BigQuery, efficiently handling over 100 million rows of dataScheduled backend tasks with airflow and demoed frontend ideas with Looker Studio

Wrote research paper on metal-organic framework efficiency, developed feature selection models in Python to contribute to gas storage and adsorption