Nathan Cole
Data Scientist
Summary
Data scientist with 6 years of experience in machine learning, experimentation and forecasting for retail and insurance. Skilled in Python, SQL, PySpark and AWS SageMaker. Built pricing and churn models that added $4.1M in annual profit and cut model deployment time from weeks to days.
Experience
- Developed gradient-boosted churn model (XGBoost) that improved retention-campaign targeting and saved $2.3M in premiums annually
- Built MLOps pipeline on AWS SageMaker and MLflow, reducing deployment time from 3 weeks to 2 days
- Designed A/B tests for 9 pricing experiments using Bayesian methods
- Mentored 3 junior data scientists on SQL, Python and model validation
- Built demand-forecasting models in Python and PySpark for 18,000 SKUs across 210 stores; forecast error down 17%
- Created markdown-optimization model that added $1.8M in gross margin per year
- Delivered Tableau dashboards for merchandising and supply-chain leaders
- Wrote SQL and Python reporting for 12 healthcare and retail clients
- Automated weekly client reports, saving 15 analyst hours per week
Education
Skills
- Python (pandas, scikit-learn, XGBoost, PyTorch)
- SQL (Snowflake, PostgreSQL)
- PySpark / Databricks
- AWS SageMaker, MLflow, Docker
- A/B testing, Bayesian statistics
- Time-series forecasting
- Tableau, Power BI
- Git, CI/CD

SlideTeam