Keeping a weather eye on prediction markets: The influence of environmental conditions on forecasting accuracy

Abstract

Prediction markets are increasingly being embraced as a mechanism for eliciting and aggregating dispersed information and providing a means of deriving probabilistic forecasts of future uncertain events. The efficient market hypothesis postulates that prediction market prices should incorporate all information relevant to the performance of the contracts traded. This paper shows that this may not be the case in relation to information regarding environmental factors such as the weather and atmospheric conditions. In the context of horseracing betting markets, we demonstrate that even after the effects of these factors on the contestants (horses and jockeys) has been discounted, the accuracy of probabilities derived from market prices are systematically affected by the prevailing weather and atmospheric conditions. By correcting for this phenomenon, we show that significantly better forecasts can be derived from prediction markets, and that these have substantial economic value.

Turning the heat on financial decisions: Examining the role temperature plays in the incidence of bias in a time-limited financial market

“…Performance (r): Costa Sperb et al (2017) show that temperature may affect the performance of both horses and jockeys. For example, they demonstrate that horses and jockeys perform better under temperatures for which they display a 'preference'.…”

“…The resulting regression coefficients are then paired with the observed temperature of race j, which then captures the forecast performance for (each) competitor i in race j given the temperature observed at race j. Further details of this methodology are provided in Costa Sperb et al (2017).…”