Brandon M. Greenwell

Data Science Leader · Applied Statistician · Open Source Author

greenwell.brandon@gmail.com · (614) 288-9450 · github.com/bgreenwell

Experience

Director, Data Science — 84.51° / Kroger, Cincinnati, OH (2022–present)

[TODO: 2–3 bullets — e.g., scope of team, strategic initiatives, key outcomes as Director of AI/ML Patterns]

Lead Data Scientist — 84.51° / Kroger, Cincinnati, OH (2018–2022)

Led Enable the Science team; drove ML/statistics best practices across 200+ data scientists through internal tooling, training, and screencasts
Built and maintained R, Python, and Spark libraries used across the enterprise; co-led ML interpretability special interest group
Contributed to COVID-19 forecast adjustment effort; supported Kroger optimization team on predictive maintenance

Adjunct Instructor — University of Cincinnati, Linder College of Business (2018–present)

Teach graduate-level data science: Applied Linear Regression (BANA 7052), Advanced Statistical Modeling (BANA 7042).

Data Scientist — Wright-Patterson AFB / USAF School of Aerospace Medicine (2015–2017)

Statistical analysis of observational medical data; developed and published R packages; delivered training in ML and R; provided statistical consultation for aerospace medicine research.

Education

Ph.D., Applied Mathematics — Air Force Institute of Technology, 2014
M.S., Applied Statistics — Wright State University, 2011
B.S., Statistics — Wright State University, 2009

Books

Greenwell, B.M. and Liu, D. (in progress). Discrete Data Analysis for Business Analytics. Chapman & Hall/CRC.
Greenwell, B.M. (2022). Tree-Based Methods for Statistical Learning in R. Chapman & Hall/CRC.
Boehmke, B.C. and Greenwell, B.M. (2019). Hands-On Machine Learning with R. Chapman & Hall/CRC.

Selected Publications

Greenwell, B.M. (under review). “Fitting Explainable Boosting Machines in R with the ebm Package.” The R Journal.
Zhu, X., Lin, Z., Liu, D., and Greenwell, B.M. (2025). “SurrogateRsq: An R Package for Categorical Data Goodness-of-Fit Analysis.” New England Journal of Statistics in Data Science, 3(1).
Greenwell, B.M., McCarthy, A.J., Boehmke, B.C., and Liu, D. (2020). “Variable Importance Plots: An Introduction to the vip Package.” The R Journal, 12(1), 343–366.
Greenwell, B.M. (2017). “pdp: An R Package for Constructing Partial Dependence Plots.” The R Journal, 9(1), 421–436.

Full publication list available on GitHub.

Open Source

Package	Description
fastshap	Fast approximate Shapley values in R (C++/Rcpp)
gbm	Maintainer of original open-source gradient boosting machine
vip	Variable importance plots; adopted by the tidymodels ecosystem
pdp	Partial dependence plots; CRAN Machine Learning task view

Skills

Languages & Tools: R · Python · Spark · SQL
Methods: Machine Learning · Interpretable/Explainable AI · Statistical Modeling · Gradient Boosting · Bayesian Inference
Leadership: Team Building · Cross-functional Collaboration · ML Platform Strategy · Technical Training