I am a PhD student in Social & Engineering Systems and Statistics at MIT working in the Clinical Machine Learning group led by David Sontag. My current research focuses on Human-AI collaboration, namely how to integrate machine learning (ML) tools in existing decision making pipelines. I have studied how to introduce an ML classifier to reduce the load on expert decision makers through the action of deferral and how to teach users of ML systems when to rely and when not to rely on an AI model. My work also aims to ensure fairness and an understanding of long-term consequences when deploying ML models.

I received my undergraduate degree in computer engineering from the American University of Beirut in 2019. In the summer of 2021 I was a resarch intern at ASAPP working with Ethan Elenberg and Ramya Ramakrishnan on learning human's mental models of AI and updating AI models to adapt to their human teammate. In the summer of 2018 I was a visiting student/intern at TTIC working with Mesrob Ohannessian and Nathan Srebro on the long term effects of fair decision making.

• Teaching Humans When To Defer to a Classifier via Examplars
  Hussein Mozannar, Arvind Satyanarayan, David Sontag
  AAAI 2022
  We develop an onboarding stage for teaching users when to rely on AI systems and when not to.

  
• Consistent Estimators for Learning to Defer to an Expert
  Hussein Mozannar, David Sontag
  ICML 2020
  We develop learning algorithms based on novel surrogate losses that know when to predict and when to defer to a human.

  
• Fair Learning with Private Demographic Data
  Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro
  ICML 2020
  We build a procedure to learn a fair predictor (e.g. satisfies equalized odds) when the demographic attributes are privatized.