Abstract: We will discuss new techniques in Artificial Intelligence and Operations Research to help mitigate homelessness and how we are working with policy-makers to deploy and evaluate them in the open world. In particular, we discuss two problems and proposed algorithms: the first one is a preference elicitation algorithm that learns the moral priorities of policy-makers in terms of policy characteristics and outcomes (e.g., fairness by race, by gender); the second one is a data-driven optimization model and approximation algorithm to help design interpretable policies that meet the desiderata of policy-makers. We show that our proposed algorithms outperform the state of the art using real data from the Homeless Management Information System database. Throughout the talk, we discuss how the research approach that we take understands and anticipates the societal challenges arising from the deployment of AI technology in the open world (e.g., introduction of bias from use of standard ML, possibility that policy-makers give irrational/inconsistent answers).
Bio: Phebe Vayanos is an Assistant Professor of Industrial & Systems Engineering and Computer Science at the University of Southern California. She is also an Associate Director of the CAIS Center for Artificial Intelligence in Society at USC. Her research aims to address fundamental questions arising in data-driven optimization (a.k.a. prescriptive analytics) with aim to tackle real-world decision- and policy-making problems in uncertain and adversarial environments. Her work is motivated by resource allocation problems that are important for social good, such as those arising in public health, public safety and security, public housing, biodiversity preservation, and education. She is also interested in issues surrounding fairness, efficiency, and interpretability in resource allocation and machine learning. Prior to joining USC, she was lecturer in the Operations Research and Statistics Group at the MIT Sloan School of Management, and a postdoctoral research associate in the Operations Research Center at MIT. She holds a PhD degree in Operations Research and an MEng degree in Electrical & Electronic Engineering, both from Imperial College London.