I’m a CS PhD student at MIT, working with David Sontag in the Clinical Machine Learning research group. My research is focused on bringing together ideas from causal inference and machine learning to build predictive models that are more robust (e.g., to dataset shift) and to improve clinical decision making using observational data.

Previously, I led the Data Science team at Clarify Health, a healthcare startup focused on population health. I also used to live in Kenya, where I helped start the McKinsey Nairobi office and managed consulting projects for government clients in Eastern and Southern Africa, including work in public health.

For my undergrad, I studied Statistics at Harvard, where I worked with Edo Airoldi on quantifing limitations of respondent-driven sampling (e.g., for measuring HIV prevalence) among hard-to-survey populations.


Characterization of Overlap in Observational Studies
Michael Oberst*, Fredrik D. Johansson*, Dennis Wei*, Tian Gao, Gabriel Brat, David Sontag, Kush R. Varshney
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
[paper], [video]

Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes
Sooraj Boominathan, Michael Oberst, Helen Zhou, Sanjat Kanjilal, David Sontag
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
[paper], [video]

Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models
Michael Oberst, David Sontag
International Conference on Machine Learning (ICML), June 2019
[paper], [slides], [poster], [video]


Primer: Learning Treatment Policies from Observational Data
Models, Inference, and Algorithms Seminar
Broad Institute, September 23rd, 2020