ANGELA ZHOU 

(+1) 646 918 4322 az434@cornell.edu 

EDUCATION 

Cornell University September 2016 -Present 
Fifth Year PhD Student, Overall GPA: 4.067 
Department of Operations Research and Information Engineering. 

Undergraduate: Princeton University. Class of 2016, Operations Research and Financial Engineering. 
Summa cum laude. 

Citizenship status: US citizen. 

RESEARCH INTERESTS 

Statistical machine learning, causal inference, data-driven decision-making under ambiguity 
(sensitivity analysis), partial identification, personalization, trustworthy machine learning. 

SELECTED PUBLICATIONS 

Author order is alphabetical, following Operations Research convention. 

Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning 

Neurips 2020 

With Nathan Kallus 

Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination 
Accepted at Management Science. 

With Nathan Kallus and Xiaojie Mao 

Minimax-Optimal Policy Learning Under Unobserved Confounding Accepted at 
Management Science. 

With Nathan Kallus 

REFEREED PUBLICATIONS 

The primary publishing venues for machine learning are selective “top-tier” refereed conferences 

(e.g. Neurips (20.8%, 21.1%, 20.1% acceptance rates), ICML (25.1%), AISTATS (33.2%,32.4%). 

Assessing Disparate Impacts of Personalized Interventions: Identifiability and Bounds 

Proceedings of Neurips 2019. 

With Nathan Kallus 

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the 
xAUC Metric Proceedings of Neurips 2019. 

With Nathan Kallus 

Interval Estimation of Individual-Level Causal Effects Proceedings of AISTATS 2019. 

With Nathan Kallus and Xiaojie Mao 


Residual Unfairness in Fair Machine Learning from Prejudiced Data Proceedings of 
ICML 2018 

With Nathan Kallus 

Policy Evaluation and Optimization with Continuous Treatments Proceedings of 
AISTATS 2018 

With Nathan Kallus 

WORKING PAPERS 

Fairness, Welfare, and Equity in Personalized Pricing 
With Nathan Kallus 
Submitted. 
Data Collection for Fair Regression 
With Miro Dudik and Jenn Wortman Vaughan. 
Paper in progress. 
HONORS/AWARDS 

Winner, INFORMS 2018 Data Mining Best Paper Award (Confounding-Robust Policy Improve


ment) 
2nd place, INFORMS 2018 Junior Faculty Interest Group Paper Competition (Confounding-
Robust Policy Improvement) 

Finalist for Best Paper of INFORMS 2017 Data Mining and Decision Analytics Workshop 
(Policy Evaluation and Optimization with Continuous Treatments) 
National Defense Science and Engineering Graduate Fellowship, awarded 2016 
Ahmet S. Cakmak Thesis prize winner for undergraduate thesis, 2016. 

PROFESSIONAL EXPERIENCE 

Microsoft Research New York City June 2019 -August 2019 

Research Intern; Mentors: Jenn Wortman Vaughan and Miro Dudik New York 

· Researched optimal data collection strategies for improving inequities in machine learning regression 
model performance across groups. 

PlaceIQ June 2016 -August 2016 

Data Science Intern New York 

· Analyzed geospatial basemap data for data analytics company assessing causal effects of online 
advertising on brick-and-mortar visitation. 

AppNexus June 2015 -August 2015 

Optimization Intern New York 

· Developed a A/B testing experiment reporting and analysis tool to analyze revenue lift of 
production experiments. 

TEACHING 


Guest lecture, Applied Machine Learning ORIE 5750 (Spring 2018, Spring 2019) 

Spring 2018: Co-organized PhD student research seminar on Fairness and Ethics in Operations 
Research 

RELEVANT COURSES 

Convex Optimization x2, Mathematical Programming (Linear), Probability Theory, Statistical 
Principles, Theoretical Machine Learning, Analysis of Algorithms, Machine Learning and 
Causality for Intelligent Decision-Making, Semi/Non-Parametric Econometrics, Bayesian Machine 
Learning, Optimal Learning, Stochastic Processes, Real Analysis 

INVITED TALKS 

Kellogg-Wharton OM Workshop (7/2020), Duke Fuqua Workshop on Operations Research and 

Data Science (12/2019). 
Assessing Algorithmic Unfairness with Unobserved Protected Class: Experian DataLab Brazil, 
(7/2020). 

Assessing Fairness of Personalized Interventions: INFORMS (11/2019) 

Towards an Ecology of Care for Data-Driven Decision Making: Cornell Digital Life Initiative 
(4/2019). 
Confounding-Robust Policy Improvement: INFORMS Conference on Healthcare (7/2019), Prince


ton (4/2019), MSR NYC (9/2018), INFORMS (11/2018) 
Residual Unfairness: Crime Lab New York (UChicago Urban Labs) (7/2018) 
Policy Evaluation and Optimization with Continuous Treatments: Spotify (7/2017), INFORMS 

(11/2017) 

SERVICE 

Workshop Co-organizing: 

• “Do the right thing: machine learning and causal inference for improved decision making”, 
Neurips 2019 
• Participatory Approaches to Machine Learning, ICML 2020 
• Workshop on Consequential Decision Making in Dynamic Environments, Neurips 2020 


Reviewer (conferences): Neurips 2019 (top 400 reviewer)-2020, ICML 2019 (top 5%) -2020 (top 
33%), FAT* 2020, AAAI Emerging Track on AI for Social Impact 2020, UAI 2019. 

Refereeing (journals): Management Science, Journal of Machine Learning Research, Statistics 
in Medicine, ACM Computing Surveys 

Program Committee (incl. reviewing): IJCAI Workshop for Social Good 2019, Theoretical 
Foundations of Machine Learning ICML 2020 workshop, AI in Financial Services Neurips 2020 
workshop, MD4SG Conference 2020