Target's famous pregnancy prediction and the ability of Google Trends to predict flu incidence aren't exactly revelations.
He noted that much had been written about predicting flu epidemics by looking at Web searches for "flu," but noted that the predictions did not improve significantly on what could already be found in data from the Centers for Disease Control and Prevention.
Dr. Philip Polgreen, an author of a recent study looking at using the Twitter stream to track flu activity, agrees that the utility of using social media to predict flu, at least, is modest.
Go to google.org/flutrends and you'll see one result: by collating searches with certain keywords Google is better able to predict flu outbreaks than the Centre for Disease Control in Atlanta.
In a study published in Nature in February, Google demonstrated how this technique was able to predict flu outbreaks in America a week or more before the government's Centres for Disease Control did.Such "rumour registries" are useful, but any leads must be validated by boots on the ground.
In the last few years, governments, businesses, humanitarian organizations and citizens have been using Big Data to accomplish feats ranging from analyzing Google search queries to predict flu outbreaks, to helping the U.S. government better understand the needs of people impacted by natural disasters, like Hurricane Sandy.
From that, they concluded that by identifying and monitoring central individuals in a given population, it might be possible to predict flu outbreaks in advance.
The power of these models was illustrated in a 2010 study by two professors and long-time collaborators Nicholas Christakis from Harvard University and James Fowler from the University of California, San Diego who found that social network analyses can predict flu outbreaks earlier than traditional tracking methods.
Researchers who tracked flu symptoms in the friends of a group of college students during the 2009 H1N1 "swine flu" pandemic predicted the flu outbreak in the general college population with at least 2 weeks' advance notice.
