What it is and where it’s going

Prediction markets are virtual stock markets, which use the information contained in market values to make forecasts.

Prediction markets are virtual stock markets, which use the information containted in market values to make forecasts. By today, these market platforms – including the one we currently apply – exclusively rely on the implicit knowledge of groups of humans being either large crowds or expert panels. This project aims to develop and implement a prediction market with integrated trading algorithms that combines human expertise with artificial intelligence and apply it to a broad range of research questions.

In its current form, PREMIA makes use of a prediction market with Hanson’s logarithmic market scoring rule integrated. Depending on the topic, the markets count between a few dozens and 500 participants. The markets typically include both laypersons and experts in the specific fields of interest. All our markets are real money markets with traders receiving a starting capital worth 10 to 30 Euros. Depending on their gambling skills, they can increase or lose this credit. Participants cannot accumulate debt and for some markets must donate their profits to a humanitarian organization.

Related publications

Arnesen, Sveinung, and Oliver Strijbis, 2015, “Accuracy and Bias in European Prediction Markets”, Italian Journal of Applied Statistics 25(2), 123-138.
Grossmann, Igor, et al., forthcoming, “Insights into accuracy of social scientists’ forecasts of societal change”, Nature Human Behavior.
McElroy, Tucker S., and Marc Wildi. 2020. “The Multivariate Linear Prediction Problem: Model-Based and Direct Filtering Solutions.” Econometrics and Statistics 14: 112–130.
Strijbis, Oliver, Sveinung Arnesen, and Laurent Bernhard, 2016, “Using prediction market data for measuring the expected closeness in electoral research”, Electoral Studies 44, 144-150.
Strijbis, Oliver, and Sveinung Arnesen, 2018, “Explaining variance in the accuracy of prediction markets”, International Journal of Forecasting 35(1), 408-419.
Wildi, Marc, and Tucker S. McElroy. 2019. “The trilemma between accuracy, timeliness and smoothness in real-time signal extraction.” International Journal of Forecasting 35(3): 1072–1084