Aggregation mechanisms for crowd predictions
- PDF / 1,738,728 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 3 Downloads / 213 Views
Aggregation mechanisms for crowd predictions Stefan Palan1,2 · Jürgen Huber2 · Larissa Senninger2 Received: 14 May 2019 / Revised: 24 October 2019 / Accepted: 28 October 2019 © The Author(s) 2019
Abstract When the information of many individuals is pooled, the resulting aggregate often is a good predictor of unknown quantities or facts. This aggregate predictor frequently outperforms the forecasts of experts or even the best individual forecast included in the aggregation process (“wisdom of crowds”). However, an appropriate aggregation mechanism is considered crucial to reaping the benefits of a “wise crowd”. Of the many possible ways to aggregate individual forecasts, we compare (uncensored and censored) arithmetic and geometric mean and median, continuous double auction market prices and sealed bid-offer call market prices in a controlled experiment. We use an asymmetric information structure, where participants know different sub-sets of the total information needed to exactly calculate the asset value to be estimated. We find that prices from continuous double auction markets clearly outperform all alternative approaches for aggregating dispersed information and that information lets only the best-informed participants generate excess returns. Keywords Information aggregation · Asymmetric information · Wisdom of crowds JEL Classification C53 · C83 · G14
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s1068 3-019-09631-0) contains supplementary material, which is available to authorized users. * Stefan Palan stefan.palan@uni‑graz.at Jürgen Huber [email protected] Larissa Senninger [email protected] 1
Department of Banking and Finance, University of Graz, Universitätsstraße 15, 8010 Graz, Austria
2
Department of Banking and Finance, University of Innsbruck, Universitätsstraße 15, 6020 Innsbruck, Austria
13
Vol.:(0123456789)
S. Palan et al.
1 Introduction 1.1 Motivation “Wisdom of crowds”, after Surowiecki’s (2004) book of the same name, is a term used to describe the observation that the aggregate of forecasts by multiple people is often a better predictor of actual outcomes than the forecasts of experts or even the best individual forecast included in the aggregation process. A number of studies have set out to document this outperformance (e.g., Gordon 1924; Bruce 1935; Sauer 1998; Berg et al. 2008a, b) and to explore and describe which forecasters and forecasting targets most readily lend themselves to successful crowd prediction (e.g., Lorge and Fox 1958; Brown and Sauer 1993; Berg and Rietz 2003; Gruca et al. 2003; Polgreen et al. 2007; Davis-Stober et al. 2014). In the present paper, we aim to compare different mechanisms for aggregating crowd predictions in a setting with asymmetric information. We are particularly interested in the predictive accuracy resulting from these aggregation mechanisms. Our experiment includes very simple mechanisms, like the average or median of individual predictions, and more complex ones
Data Loading...
