Motivated from the problems faced by under-served communities or in under-resourced settings, we are working to define and quantify fairness in resource allocation. Our aim is to build intelligent decision-making and resource allocation systems that effectively trade-off fairness, efficiency, and transparency while being robust to uncertainty/noise in the data.

Our work in this area is motivated by our ongoing partnership with the Los Angeles Homeless Services Authority (LAHSA), the authority in charge of allocating housing resources to those experiencing homelessness in L.A. County. In particular, our objective is to assist LAHSA in continually improving their policy for allocating housing resources to the homeless so as to mitigate homelessness. We are building an integrated system for redesigning the housing allocation system at LAHSA.

We are investigating the problem of designing fair, efficient, and interpretable policies for allocating scarce resources of different types to heterogeneous allocatees on a wait list. Using data from the U.S. homeless youth, we have showed that our frameworks result in policies that are more fair than the current policy in place and than classical interpretable machine learning approaches while achieving a similar (or higher) level of overall efficiency. We are also devising frameworks for designing static and dynamic questionnaires for eliciting the moral priorities of policy-makers at LAHSA (e.g., to be able to understand and quantify their definition of fairness), see also our research on robust optimization for social good.

Our research is also motivated from discussions with transplant surgeons at Massachusetts General Hospital and by the problem of improving the system for allocating deceased donor kidneys. For example, we have investigated the problem of estimating wait times for individual patients in the U.S. Kidney Allocation System, based on the very limited system information that they possess in practice. We are interested in working with transplant surgeons to improve the chances of surval of patients awaiting for a kidney transplant.

Active preference elicitation via adjustable robust optimization

P. Vayanos, (*) D. McElfresh, (*) Y. Ye, J. Dickerson, E. Rice

Under review at Management Science, February 2020.

Robust optimization with decision-dependent information discovery

P. Vayanos, A. Georghiou, (*) H. Yu

R&R at Management Science, September 2019.

Understanding wait times in rapid rehousing among homeless youth: a competing risk survival analysis

H.-T.Hsu, E. Rice, J. Wilson, S. Semborski, P. Vayanos, M. Morton

The Journal of Primary Prevention, 2019

Linking homelessness vulnerability assessments to housing placements and outcomes for youth

E. Rice, M. Holguin, H.-T.Hsu, M. Morton, P. Vayanos, M. Tambe, and (*) H. Chan

Cityscape, 20(3), Office of Policy Development and Research (PD&R) of the US Department of Housing and Urban Development (HUD), 2018.

Robust multiclass queuing theory for wait time estimation in resource allocation systems

C. Bandi, N. Trichakis and P. Vayanos

Management Science, 65(1), pp. 152-187, 2018.

The street-level realities of data practices in homeless services provision

(*) N. Karusala, (*) J. Wilson, P. Vayanos, E. Rice

In Proceedings of the 22nd ACM on Human-Computer Interaction 3, CSCW, 2019.

From empirical analysis to public policy: evaluating housing systems for homeless youth

(*) H. Chan, E. Rice, P. Vayanos, M. Tambe, and M. Morton

In Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2018.

Designing fair, efficient, and interpretable policies for prioritizing homeless youth for housing resources

(*) M. J. Azizi, P. Vayanos, B. Wilder, E. Rice and M. Tambe

In Proceedings of the 15th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR), 2018.

Invited to Constraints journal fast track for outstanding papers.

Evidence from the past: AI decision aids to improve housing systems for homeless youth

(*) H. Chan, E. Rice, P. Vayanos, M. Tambe, and M. Morton

In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) 2017 Fall Symposium Series, 2017.