“Eva,” an algorithm designed by the University of Southern California’s Marshall School of Business and the Wharton School of Business at the University of Pennsylvania, was used by Greece after the country reopened to visitors to track asymptomatic cases of COVID-19.
A new study shows that Greece’s use of the computer program may have helped curb the viruses spread throughout the country.
“It was a very high-impact artificial intelligence project, and I believe we saved lives by developing a cutting-edge, novel system for targeted testing during the pandemic,” said Kimon Drakopoulos, an assistant professor of data sciences and operations at USC Marshall and one of the authors on the study.
Greece depends on its typically lively tourist season, and was set on finding the safest and most effective strategy for allowing visitors during the pandemic.
Working together with USC and Wharton, the country developed Eva, an algorithm that tracks real-time data and selects high-risk travelers for COVID testing. The study found that the program was able to catch double the amount of asymptomatic tourists then they would have if they had only used travel restrictions and randomized testing.
“Our work with Eva proves that carefully integrating real-time data, artificial intelligence and lean operations offers huge benefits over conventional, widely used approaches to managing the pandemic,” said Vishal Gupta, a USC Marshall associate professor of data science and operations and another author on the study.
Greek data scientist at USC got the idea for the Eva algorithm after seeing Greece’s reopening announcement
Drakopoulos, who is Greek himself and studied at the National Technical University of Athens, got the idea for the project after seeing Greece’s inital plans to reopen to visitors in the summer of 2020.
Drakopoulos was able to contact Prime Minister Kyriakos Mitsotakis directly to get a better understanding of Greece’s plans and ended up offering the PM his help.
After meeting with Mitsotakis, USC Marshall, Wharton School researchers and AgentRisk CEO Jon Vlachogiannis joined in a partnership with Greece to create Eva for tracking COVID cases. Because of the supply chain disruptions in the earlier months of the pandemic, the country only had a limited amount of COVID tests, but was tasked with identifying travelers who had been infected before passing through one of the 40 different entries into the county.
Eva was used by the Greek government to organize huge amounts of data submitted by tourists. Eva was able to create profiles for each traveler based on where they had stayed and visited, as well as their country of origin, gender, and age.
“At the beginning of the cycle, travelers interested in going to Greece fill out a form online,” said Gupta. “They share information like where they’ve been before, demographic information and their travel itinerary. Based on that information, we — and Eva — were able to recommend who should be tested.”