We compare predictions from a conventional protocol-based approach to risk assessment with those based on a machine-learning approach. We first show that the conventional predictions are less accurate than, and have similar rates of negative prediction error as, a simple Bayes classifier that...

Exploiting the near-experimental conditions provided by the British Pound market in US Dollars during the Brexit vote of June 23rd, 2016, we unearth a major challenge to the Efficient Market Hypothesis. With a single factor of prior polling information, we show that the Brexit result could have...