I’m a data scientist currently working at Capital One where I leads the development of specialty underwriting models and serve as a Model Risk Officer for fraud models.
Over the past decade, I’ve has worn all the hats in the data space with work spanning data analysis (inference and measurement), data engineering (analyst tools, data pipelines, data products), and data science (core machine learning). I’m passionate about bridging the gaps between these disciplines. While navigating large enterprise settings, Emily has also served as a “data team of one” for many pro-bono projects and data-driven voter turnout initiatives across 8+ states.
Outside of work, I enjoy supporting open source software and the free flow of information. I promote open science by serving on the editorial board of rOpenSci, on the technical advisory board of Bluebonnet Data, and as a volunteer statistical textbook reviewer for Routledge / CRC Press. My own writing and past talks (found here!) center on developing reproducible workflows and exposing the tacit knowledge of data work.
Outside of outside-of-work work, I enjoy reading, running and weighlifting while listening to podcasts on 2.5x, Carolina basketball, and spending time with my chihuahua and niblings.