I develop methods, applications, and tools to investigate and support learning in large-scale digital environments. More broadly, my work touches on statistical and computational methods for learning from massive datasets and conducting dynamic personalization in a reproducible and scalable way. This work supports machine learning and data mining with learner data at scale and has potential applications for adaptive interventions and learner pathways, reproducible computational research, and applied machine learning.
My work has addressed diverse questions relevant to many domains, including high-dimensional model selection, network-augmented classification, and reproducible research with massive private datasets. A key focus area of my work is developing tools and methods for robust and reproducible data science research in both computer science and applied statistics, and in applying those tools to drive real-world impact.
In Fall 2018, I will be beginning a PhD in computer science at the University of Washington's Paul G. Allen School of Computer Science and Engineering.