In the name of accuracy, Google retools its Flu Trends model

Google has developed a new model for its Flu Trends tool that attempts to predict the intensity of flu season across the world based on the number of searches for certain flu-related terms. Launched in 2009, the original Flu Trends model has performed pretty well, but over-predictions (sometimes significant) over the past couple years have led to a spate of criticism over Google’s methodology.

Whether that criticism is fair or not, [company]Google[/company] has heeded it and retooled the Flu Trends model to include data from the Centers for for Disease Control and Prevention throughout flu season rather than just to initially train the model and establish a baseline. Research published earlier this year showed that models combining Google’s data with the CDC’s data actually perform best of all. That shouldn’t be surprising: although some researchers criticized Google’s “big data” approach, a truer big data approach would combine data from multiple sources in order to get a more complete picture.

The new model is only in effect for the United States this season, but, as Google senior software engineer Christian Stefansen wrote in the blog post announcing it, “We look forward to seeing how the new model performs in 2014/2015 and whether this method could be extended to other countries.”

Here’s what Google’s new Flu Trends model is seeing so far this year.