This spring Greece, a country for which tourism is a key part of its economy, faced a dilemma. Whether to open its gates to foreign travelers amidst the pandemic. The country has been in a nationwide lockdown since November 7, 2020. A night-time curfew is in force, the country’s regions are classified as “red” (high alert) or “deep red” (very high alert) zones, and citizens must send a text message (SMS) or fill in a document to justify any exit from their homes. Otherwise, they face heavy fines.

The reports coming out of the country this week are also not good, as the number of cases is steadily increasing from last week.

Despite the government’s warning, many tourists, including Americans are flying to the country many carrying the virus unknowingly. To test and quarantine all these tourists is a humungous job for the government.

Amidst this chaos what is becoming a key tool for the country in effectively testing the tourists with available resources and infrastructure is Eva, a machine learning platform Kimon Drakopoulos, and Vishal Gupta two data scientists at USC Marshall School of Business developed this summer along with Hamsa Bastani, an assistant professor of operations, information and decisions from the Wharton School at the University of Pennsylvania; Jon Vlachogiannis, founder of AgentRisk; and the Greek government.

“We built an artificial intelligence system to help Greece safely reopen its borders to over 80,000 tourists a day. The system, known as Eva, determined which foreign visitors to admit and who to target for testing. As schools, businesses, and tourist destinations navigate a new wave of coronavirus cases amid the busy holiday season, they should consider how to use data and artificial intelligence to deploy their testing resources efficiently and reduce the spread of the virus” Explains Bastani in a recent paper titled “Deploying an Artificial Intelligence System for COVID-19 Testing at the Greek Border,”

The results show that Eva has been 1.85 times efficient than the conventional random checking of passengers. “Our work paves the way for leveraging [artificial intelligence] and real-time data for public health goals, such as border control during a pandemic,” the paper stated. With the rapid spread of a new coronavirus strain, Eva also holds the promise of maximizing the already overburdened testing infrastructure in most countries.

“The main issue was, given the fixed budget for tests, whether we could conduct the tests in a smarter way with dynamic surveillance to identify more infected travelers,” said Bastani