George H. Chen

Timeline

1. 2010

   Engineering and mathematics at Berkeley

   He earns a BS at the University of California, Berkeley, in 2010, with dual majors in Electrical Engineering and Computer Sciences and Engineering Mathematics and Statistics.

2. 2012–2015

   Graduate study at MIT

   At MIT's Department of Electrical Engineering and Computer Science, he earns an SM in 2012, an Electrical Engineer degree in 2014, and a PhD in 2015. He receives MIT's Goodwin Medal for graduate student teaching in 2015.

3. January 2016

   MITx fellow and GridForm

   In January 2016, he works as an MITx postdoctoral teaching fellow and helps develop GridForm at MIT's Tata Center for Technology and Design. The system uses satellite images and machine learning to model villages and plan microgrids for rural India.

4. May 2018

   A book on nearest neighbors

   In May 2018, he and Devavrat Shah publish Explaining the Success of Nearest Neighbor Methods in Prediction. The monograph explains statistical guarantees for predicting from similar training examples and methods for scaling nearest-neighbor search.

5. August 2020

   Deep kernel survival analysis

   He introduces Deep Kernel Survival Analysis and Subject-Specific Survival Time Prediction Intervals at the 2020 Machine Learning for Healthcare conference. The method uses a neural network to learn how individuals are compared and produces intervals that express uncertainty in predicted survival times.

6. March 2022

   An NSF CAREER award

   In 2022, while an assistant professor of information systems at Heinz College and affiliated with Carnegie Mellon's Machine Learning Department, he receives an NSF CAREER award of nearly $585,000. The project develops machine learning models to predict patient recovery times and hospital stays.

7. 2024

   Survival kernets

   In 2024, he publishes Survival Kernets: Scalable and Interpretable Deep Kernel Survival Analysis with an Accuracy Guarantee in the Journal of Machine Learning Research. The model groups training data into clusters that can be displayed to help explain individual survival predictions, and he establishes a bound on prediction error for a special case.

8. October 2024

   A guide to survival models

   In October 2024, he releases An Introduction to Deep Survival Analysis Models for Predicting Time-to-Event Outcomes. The monograph explains neural network methods for predicting when events occur and covers fairness, causal reasoning, interpretability, and statistical guarantees.

9. December 2025

   An ML4H paper award

   With Xiaobin Shen, he receives the Models and Methods Best Paper Award at Machine Learning for Health in December 2025 for Deep Kernel Aalen-Johansen Estimator. Their paper presents an interpretable neural network framework for competing risks.

10. As of October 2026

    Associate professor at Carnegie Mellon

    As of October 2026, he is an associate professor at Carnegie Mellon University's Heinz College of Information Systems and Public Policy and an affiliated faculty member of its Machine Learning Department. His research focuses on trustworthy machine learning for predicting time-to-event outcomes and analyzing medical time series. He is also a co-founder and adviser to CoolCrop, which provides farmers in India with cold storage and market forecasts.