Skip to main content


Online - COVID-19: A Surprisingly Effective Data Driven Model

Thursday, July 9, 2020

11:00 am - 12:00 pm

About the Event

 The speaker, Marco Sampaio, will provide an analysis of a publicly available dataset for COVID-19, including infection and mortality-related data. He will focus on the merits and shortcomings of purely data driven models as opposed to models which attempt to capture details of the dynamics of the process. After a brief overview of known approaches, an analysis of the uncertainty of the predicted model parameters will be explored, with comparisons by country. Finally, the pros and cons of Dash/Plotly and Heroku (for deployment) will be discussed.


Speaker Bio

Marco Sampaio is a research data scientist at Feedzai. Originally trained as a theoretical physicist, he received his bachelor degree at the University of Porto and graduated with his master’s degree and doctorate from the University of Cambridge. Before embracing the world of data science in industry, he worked on topics as diverse as cosmological models, black hole physics and theoretical particle physics. Employed for a while with CERN, Sampaio is currently working on machine learning algorithmic solutions in data streaming scenarios in order to fight fraud. He admittedly is “thoroughly addicted to research, problem solving and equations.”



Online streaming
Martin Huarte-Espinosa
Associate Director
HPE Data Science Institute