Associate Professor, Heinz College of Information Systems and Public Policy
Affiliated Faculty, Machine Learning Department
Carnegie Mellon University
Email: georgechen [at symbol] cmu.edu
Research overview: I study trustworthy machine learning methods for reasoning about time, often in the context of health applications. Much of my work is on predicting time durations before critical events happen (also called "time-to-event prediction" or "survival analysis"), or on analyzing time series such as electronic health records and EEG data. I am interested in developing new methods for these time-related problems as well as understanding when and why these methods work in terms of statistical guarantees. In these endeavors, I have worked extensively on "nonparametric" methods that work under very few assumptions on the data.
Professional service: This year, I'm serving as an area chair for ICML, NeurIPS, and MLHC. For other activities I've been involved with, please see my CV.
Time-to-event prediction/survival analysis: How much time will elapse before a coma patient wakes up, a disease relapses, or a customer cancels a subscription service? These time durations are examples of what are called "time-to-event outcomes". I have a new book/monograph (published December 2024) in Foundations and Trends in Machine Learning that aims to be a reasonably self-contained introduction to deep learning methods for predicting time-to-event outcomes, targeted toward a machine learning audience; a preprint is on arXiv. Previously, I taught a survival analysis tutorial at CHIL 2020 and at SIGMETRICS 2021, and I co-organized a survival analysis symposium as part of the 2023 AAAI Fall Symposium Series.
CoolCrop: I occasionally also work on machine learning for the developing world. I co-founded and now am an advisor for CoolCrop, an AgriTech startup based in India that works on providing farmers with cold storage units (such as a refrigerator shared by a village) and market forecasts. We currently serve over 9000 farmers across 7 states in India at over 40 sites.
My educational background:
- PhD in Electrical Engineering and Computer Science, MIT, June 2015
- SM in Electrical Engineering and Computer Science, MIT, June 2012
- BS with dual majors in Electrical Engineering and Computer Sciences and in Engineering Mathematics and Statistics, UC Berkeley, May 2010
Teaching: At CMU in spring 2025 mini 4, I am teaching "Unstructured Data Analytics" to public policy master's students (course number 94-775) and to information systems master's students (95-865). I also taught a guest lecture on survival analysis for 36-736 "Methods for Correlated Data and Bayesian Statistics 2".