Pandemic Response Challenge

The $500K Pandemic Response Challenge, required teams to build effective data-driven AI systems capable of accurately predicting COVID-19 transmission rates and prescribing intervention and mitigation measures that, with testing in “what-if” scenarios, were shown to minimize infection rates as well as negative economic impacts. 

The goal for the competition is to build a collaborative AI-For-Good ecosystem to assist in developing regional plans for COVID-19 and future pandemics, resulting in:

• More data
• Better predictions
• Better intervention plans
• Easier path for implementing good intervention plans
• Continual improvement as new data, and new interventions such as vaccination and treatments become available
• Demonstration of improved problem solving by synergizing human knowledge and predictive/prescriptive modeling
• Provide a platform for faster interventions in the future
• Provide blue-print for how to create an AI-for-good global collaborative effort to tackle problems of the scale of the pandemic

WINNERS

1ST PLACE: VALENCIA IA4COVID19

Winning first place and $250,000 is team VALENCIA IA4COVID19 (Valencia, Spain), coordinated by Dr. Nuria Oliver, Commissioner of the Presidency of the Generalitat Valenciana and J. Alberto Conejero, Director of the Applied Mathematics Department at Universitat Politècnica de València. VALENCIA IA4COVID19 has collaborated with the Valencian government since March 2020 to leverage data science in the fight against COVID-19. Ultimately, the team’s winning models successfully forecasted epidemiological evolution through their use of AI and data science and provided decision makers with the best prescriptor models to produce non-pharmaceutical intervention plans that minimize the number of infections while minimizing the stringency of the interventions.

Learn more about Team VALENCIA IA4COVID19 HERE.

2ND PLACE: JSI vs COVID

In second place and $250,000 is team JSI vs COVID (Ljubljana, Slovenia), whose team members were previous competitors in the Qualcomm Tricorder XPRIZE. JSI vs COVID worked to develop accurate predictors of COVID-19 infections using a combination of a SEIR epidemiological model and machine learning and successfully modeled the trade-offs necessary when weighing public health interventions and economic impact.

Learn more about team JSI vs COVID: LINK

Through the Challenge, both teams hope to achieve more accurate models for predicting the evolution of COVID-19 and Intervention Plan prescription models that can be used in their respective countries and beyond. These top-performing teams were selected from among 48 finalists in 17 countries. In total, over 100 teams from throughout the world initially joined the competition.

Learn more about the technical results of the Challenge here. 

HONORABLE MENTIONS

In addition to the two grand prize winners, eight additional teams have received honorable mentions and will each receive $3,000 in AWS credits for cloud and compute services, courtesy of AWS, a supporting partner of the Challenge. These teams are:

• metis2020 (Los Angeles, Calif., US)
• mvsm (Berlin, Germany)
• CoronaSurveys (Madrid, Spain)
• Nixtamal AI (Mexico City, Mexico)
• Shanvi (San Diego, Calif., US)
• Kangaroos (Sydney, Australia)
• ADVANCE4COVID (Rochester, MN, US)
• Nebraska team (Omaha, Nebr., US)

WHAT’S NEXT

Moving forward, XPRIZE and Cognizant, along with ITU and additional partners, are expanding these efforts beyond the scope of this competition to one of a public platform and ecosystem that encourages the convening of AI and data while enabling the contributions of experts and thought leaders of the global community of public health. We urge those interested to join and contribute to these efforts to reach out by contacting XPRIZE at [email protected].