Developing the Theory and Practice of Epidemiological Forecasting

December 2016: CDC has just named us “Most Accurate Forecaster” for 2015-2016. (Results )

October 2017: We did it again! Our two systems took the top two spots out of 28 submissions in the 2016-2017 flu challenge. (Results )

October 2018: and yet again! Our forecasting systems took #1 in each of the three separate flu forecasting challenges of 2017-2018 (out of up to 30 submissions). (Results )


Epidemiological forecasting is critically needed for decision making by public health officials, commercial and non-commercial institutions, and the general public. The Delphi group at Carnegie Mellon University focuses on developing the technological capability of epi-forecasting, and its role in decision making, both public and private. Our long term vision is to make epidemiological forecasting as universally accepted and useful as weather forecasting is today.

Operational Systems


We have participated, and have done very well , in all epidemiological forecasting challenges organized by the U.S. government to date:


Roni Rosenfeld

Ryan Tibshirani

Logan Brooks

David Farrow

Jiaxian (Chris) Sheng

Maria Jahja

Theresa Gebert

Aaron Rumack

Nicholas Trieu

Steven Abreu

We are faculty and students at Carnegie Mellon University (some alumni ). We are also part of a larger, University of Pittsburgh-based MIDAS National Center of Excellence , which includes epidemiologists, virologists, public health experts, infectious disease MDs, legal and economic experts, and other computationalists.

Publicly Available Tools

Source codes are freely available on GitHub .

Ongoing Research Projects


We are thankful for generous financial support from