What we learned from predicting the 2016 US presidential election

As we approach the end of 2016, what feels like a very long election cycle in the US is finally coming to an end, complete with what, for many, was a surprising conclusion based on the pre-election polls (or, more accurately, how those polls were interpreted). Given the pre-election polls and the subsequent critical press coverage, it is natural to wonder whether the data presented in various 2016 presidential election predictions had some "issues". Four years ago we were interested in how data analytics could be used in pre-election polling to make it statistically more accurate so we created an… [Continue Reading]