Abstract
We use data from betting markets to analyze the sensitivity of stock returns to potential outcomes of political events such as elections. By classifying stocks into expected conditional winners and losers prior to such an event, we form portfolios that generate large positive returns after the event date, conditional on correctly anticipating the outcome. The approach is illustrated using data from the 2016 US presidential election and the 2016 Brexit referendum. We show that these sensitivities contain information about event-related returns beyond that of firm characteristics whose predictive power has been documented in the literature.