- Hamsa Bastani, Assistant Professor, Wharton School, University of Pennsylvania
- Benjamin Fels, CEO, MACRO-EYES
- Florin Ciocan, Assistant Professor, INSEAD
- Nita Madhav, CEO, MetaBiota
- Marelize Gorgens, Lead, Digital Health, World Bank
- Kay van der Horst, Managing Director, Pandemic Prevention Institute, Rockefeller Foundation
- Prashant Yadav, Senior Fellow, Center for Global Development
There have been several explorations and a few impactful uses of Machine Learning (ML) and advanced analytics during the COVID-19 pandemic. A lot of the discussion around the use of ML has centered around their use for case projections, accelerating the development of vaccines and treatments, and new forms of AI/ML based diagnostic tools for COVID19. However, ML models have also been used to design more precise and targeted pandemic responses and in better planning for future pandemics. Examples include targeted on-arrival testing at airports and borders; design of targeted lockdowns to balance economic and epidemiological considerations; algorithms for targeting primary care clinics for vaccine deployment; and the use of satellite, social networking, and mobility data to understand compliance to Nonpharmaceutical Interventions (NPIs). To realize the full potential of machine learning models in future pandemic preparedness and response, we need to better understand the conditions under which such models can be useful in supporting policy decisions; and create ways to ensure that the model inputs are appropriate, well-grounded, and at the right level of aggregation. This event will explore some of these issues, starting with a series of short research talks followed by two policy keynotes.