“The past does not repeat itself, but it rhymes."- Mark Twain Although future events have unique circumstances, they typically follow familiar past patterns. Over the past few years, I devoted my life to the development of prediction techniques based on mining such patterns—inferring the first Cholera outbreak in Cuba in 130 years, genocide events and riots in Sudan. The algorithms I developed deal with the complexity of discovering such patterns by harvesting large-scale digital histories, social and real-time media and human web behavior, and augmenting them with human knowledge mined from the web, to deliver real-time estimations of the likelihood of future events. My recent efforts included applying such methods in order to predict events in the economy, which will be described in this talk.