Data Engineer & Data Scientist — Python · SQL · Airflow · AWS · Spark · scikit-learn

Purdue alum building data pipelines and ML systems that turn messy data into clear decisions. Currently open to full-time Data Engineer and Data Scientist roles.

🌐 Portfolio: portfolio-green-eta-59.vercel.app

• Languages: Python, SQL, JavaScript
• Data & ML: pandas, scikit-learn, NumPy, Jupyter, Streamlit
• Engineering: Airflow, Spark, AWS, Docker, REST APIs
• Viz & Reporting: matplotlib, seaborn, Quarto, Vite

RandomForest model predicting NCAA bracket selections by quantifying geographic fan bias. 67% accuracy on 76k+ brackets using Haversine distance features and KenPom analytics. scikit-learn pipeline + interactive Streamlit dashboard.

Python tooling that bulk-creates and standardizes ClickUp task hierarchies from JSON templates — turns multi-hour project setup into a one-command run. Tests included.

EDA on retail shopper data — pandas/seaborn pipeline producing customer-segment insights and pairplot visualizations.

Jupyter analysis project with Quarto-rendered HTML reports — reproducible workflow from raw data to publishable findings.

• 📫 Email: mlwhitfi24@gmail.com
• 💼 LinkedIn: michael-whitfield-jr