New Time Series Methods for Flu Forecasting

There has been recent concerted interest in computational methods for forecasting the flu, spurred by competitions organized by agencies like the CDC and IARPA. The CDC competition aimed to forecast flu seasonal characteristics in the US and the IARPA Open Source Indicators (OSI) forecasting tournament was focused on disease forecasting (flu and rare diseases) in countries of Latin America. The speaker's team was declared the winner in the IARPA OSI competition and this task will communicate our lessons learned about what goes into a successful flu forecasting engine, how to evaluate its performance, and how best to ensure its relevance to public health policy and planning purposes.