Ryan Tibshirani

Keynote Talk: Delphi's COVIDcast Project: An Ecosystem for Tracking and Forecasting the Pandemic

2020 Responsible Machine Learning Summit: AI and COVID-19

 

Ryan Tibshirani
Ryan Tibshirani, Associate Professor of Statistics and Machine Learning, Carnegie Mellon University

Keynote Talk: Delphi's COVIDcast Project: An Ecosystem for Tracking and Forecasting the Pandemic 

Abstract: The Delphi group is a CMU-based group of researchers who work on epidemic tracking and forecasting. When the COVID-19 pandemic arrived, we focused all our attention on it, and launched an effort to support the US COVID response, called COVIDcast. The COVIDcast project has many parts:

1. Unique relationships with partners in tech and healthcare granting us access to data on pandemic activity.
2. Code and infrastructure to build COVID-19 indicators, continuously-updated and geographically comprehensive.
3. A historical database of all indicators, including revision tracking, currently with over 500 million observations.
4. A public API serving new indicators daily (and R and Python packages for client support).
5. Interactive maps and graphics to display our indicators.
6. Forecasting and modeling work building on the indicators.

In this talk, I will summarize the various parts, and highlight some interesting findings so far. I'll also describe ways you can get involved yourself, access the data we've collected, and leverage the tools we've built. This talk reflects the contributions of many people (most of whom volunteered their time once the pandemic began). 

Biography: I am an Associate Professor jointly appointed in the Departments of Statistics and Machine Learning at Carnegie Mellon University. I joined the Statistics faculty at Carnegie Mellon University in 2011, and I joined the Machine Learning faculty in 2013. I did my Ph.D. in Statistics at Stanford University in 2011. My thesis advisor was Jonathan Taylor. Before that, I did my B.S. in Mathematics at Stanford University in 2007.

My research interests lie broadly in statistics, machine learning, and optimization. More specifically, my interests include high-dimensional statistics, nonparametric estimation, distribution-free inference, graphs, optimization, and numerical analysis. My main applied focus at this time is on methods for forecasting epidemics (primarily seasonal flu).