Informational Efficiency and Behaviour Within In-Play Prediction Markets

We propose a practical framework to detect mispricing, test informational efficiency and evaluate the behavioural biases within high-frequency prediction markets, especially in how prices react to news. We show this using betting exchange data for association football, exploiting the moment when the first goal is scored in a match as major news that breaks cleanly. There is mispricing in these markets and inefficiency, explained by a reverse favourite-longshot bias. This is systematically absorbed or amplified after a goal, depending on the time elapsed in the match and whether the markets expect a close match before kick-off. We find that prices respond correctly when news is expected but overreact when it is a surprise. Price movements are consistent with market participants who interpret major news in a way which confirms their prior beliefs