I build the pipelines, packages, and internal tools that turn your raw data into a reproducible, insight-ready asset. I specialize in replacing fragile, undocumented workflows with clean, modular systems your team can actually maintain and build on.

• —Patient-level cohort and feature engineering pipelines
• —R package development (open-source or internal)
• —Replacing legacy SQL workflows with reproducible, readable code
• —Analytics dashboards and reporting automation

I translate complex datasets into simple, transparent decision tools that clinicians, operators, and executives can actually use. Drawing on my academic work in decision science, I build fast-and-frugal models and decision frameworks that prioritize clarity and trust over algorithmic complexity.

• —Fast-and-frugal decision trees for clinical triage and risk stratification
• —Explainable model development and validation
• —Decision frameworks for non-technical stakeholders
• —Benchmarking simple vs. complex models on your data

I've taught data science and decision-making to over 500 students and professionals across academia and industry. I design and deliver workshops, short courses, and training programs that build real, lasting capability — not just familiarity with tools.

• —Hands-on R workshops for research and clinical teams
• —Decision science and applied statistics short courses
• —Reproducible research practices for data science teams
• —Custom curriculum design for internal onboarding programs