Interpretable OR for High-Stakes Decisions: Designing the Greek COVID-19 Testing System

29 Pages Posted: 9 Sep 2021

See all articles by Hamsa Bastani

Hamsa Bastani

University of Pennsylvania - The Wharton School

Kimon Drakopoulos

University of Southern California

Vishal Gupta

Data Science and Operations, Marshall School of Business

Date Written: July 30, 2021

Abstract

In the summer of 2020, in collaboration with the Greek government, we designed and deployed Eva – the first national scale, reinforcement learning system for targeted COVID-19 testing. In this paper, we detail the rationale for three major design/algorithmic elements: Eva’s testing supply chain, estimating COVID-19 prevalence, and test allocation. Specifically, we describe the design of Eva’s supply chain to collect and process thousands of biological samples per day with special emphasis on capacity procurement. Then, we propose a novel, empirical Bayes estimation strategy to estimate COVID-19 prevalence among different passenger types with limited data and showcase how these estimates were instrumental for a variety of downstream decision-making. Finally, we propose a novel, multi-armed bandit algorithm that dynamically allocates tests to arriving passengers in a non-stationary environment with delayed feedback and batched decisions. All of our design and algorithmic choices emphasize the need for transparent reasoning to enable human-in-the- loop analytics. Such transparency was crucial to building trust and buy-in among policymakers and public health experts in a period of global crisis.

Note: Funding: V.G. was partially supported by the National Science Foundation through NSF Grant CMMI-1661732.

Declaration of Interests: H.B., V.G., and J.V. declare no conflict of interest. K.D. declares non-financial competing interest as an unpaid Data Science and Operations Advisor to the Greek Government from May 1st, 2020 to Nov 1st, 2020.

Keywords: targeted COVID-19 testing, human-in-the-loop analytics, supply chain design, empirical Bayes, LASSO, reinforcement learning

Suggested Citation

Bastani, Hamsa and Drakopoulos, Kimon and Gupta, Vishal, Interpretable OR for High-Stakes Decisions: Designing the Greek COVID-19 Testing System (July 30, 2021). Available at SSRN: https://ssrn.com/abstract=3916367 or http://dx.doi.org/10.2139/ssrn.3916367

Hamsa Bastani (Contact Author)

University of Pennsylvania - The Wharton School ( email )

3641 Locust Walk
Philadelphia, PA 19104-6365
United States

Kimon Drakopoulos

University of Southern California ( email )

Marshall School of Business
Los Angeles, CA 90089
United States

Vishal Gupta

Data Science and Operations, Marshall School of Business ( email )

Marshall School of Business
BRI 401, 3670 Trousdale Parkway
Los Angeles, CA 90089
United States

HOME PAGE: http://www-bcf.usc.edu/~guptavis/

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
18
Abstract Views
92
PlumX Metrics