ARC23 Keynote Speaker Roni Rosenfeld

Epidemic Tracking and Forecasting: Pandemic Lessons for Technologists

Roni Rosenfeld, Professor and Head, Machine Learning Department, School of Computer Science, Carnegie Mellon University

Abstract
The Delphi group at Carnegie Mellon University was established in 2012 to develop the theory and practice of epidemiological forecasting, with a long-term vision of making this technology as universally accepted and useful as weather forecasting is today.  During the Covid-19 pandemic, we received tremendous support from government, industry, foundations and many volunteers in our attempt to provide useful real-time information to CDC, state and local public health agencies, healthcare providers, civic leaders, data journalists and the public.  As the pandemic emergency waned, we have been returning to our original long-term goal. I will discuss our successes and failures during the past three years, and the lessons we learned along the way.

Biography
Roni Rosenfeld describes the Delphi group's vision as making epidemiological forecasting as universally accepted and useful as weather forecasting is today. The group develops both machine learning and human-in-the-loop techniques for real-time estimation of geographically detailed epidemic prevalence from diverse data sources, and for forecasting the trajectory of these epidemics across time and space. The group has won most of the epidemic forecasting competitions run by the CDC to date and was recently designated a National Center of Excellence for Flu Forecasting.

Roni Rosenfeld earned a BS in mathematics and physics at Tel-Aviv University, and MS and PhD in computer science at Carnegie Mellon University. At CMU, he is head of the Machine Learning Department and professor of machine learning, language technologies, computer science, and computational biology, in the School of Computer Science. He also holds a courtesy appointment at CMU's Heinz School of Public Policy at , and an adjunct appointment at the Pitt School of Medicine.

He has been teaching machine learning and statistical language modeling since 1997. He has taught thousands of undergraduate and graduate students, been a mentor to five post-doctoral students and an advisor to about a dozen Ph.D. students and a score of master’s and undergraduate students. His current interests include tracking and forecasting epidemics, using speech and language technologies to aid international development, using machine learning for social good, and advancing data numeracy for all. He has also performed research in statistical language modeling, machine learning, speech recognition and viral evolution. He has published well over 100 scientific articles in academic journals and conferences.

Rosenfeld is a recipient of the Spira Teaching Excellence Award and twice the recipient of the Allen Newell Medal for Research Excellence.