Modelling Fixed Odds Betting for Future Event Prediction

Prediction markets provide a promising approach for future event prediction. Most existing prediction markets are built upon auction mechanisms. Although powerful and flexible in some contexts to capture signals of events, these mechanisms 1) mix opinions from experts and amateurs; 2) require continuous attention from the participants and limit possible information sources; and 3) are subject to various forms of market manipulation. To alleviate these limitations, we propose to employ the classic fixed odds betting as a prediction market. In this research, we build a structural model based on a Belief-Decision framework as the event probability estimator of the market. The Belief-Decision framework models bettors’ belief with mixed beta distributions and bettors’ decisions with prospect theory. We took a maximum likelihood approach to estimate the parameters of model and conducted experiments on three real-world betting datasets to evaluate its performance. Experimental results show that our proposed approach outperforms the (standard & customized) reduced form models and have a comparable performance with auction-based prediction markets. The results indicate the possibility to employ fixed odds betting as a prediction market.