Abstract
In many contexts, people generate forecasts about events of interest, and decision-makers wish to aggregate these forecasts to improve their accuracy. These forecasts differ from signals in the physical sciences. In particular, sensor signals are noisy samples from a common underlying distribution, while human-generated forecasts are based on cognitive models that vary from one informant to another. As a result, human forecasts, unlike physical signals, are not guaranteed to be statisticallyindependent conditioned on the true outcome. These differences both provide new opportunities for aggregation, and impose restrictions that do not apply to physical signals. This paper describes the difference between forecasts and physical signals, outlines a strategy for exploiting these differences in aggregation, and demonstrates modest but statistically significant gains in the accuracy of aggregated forecasts using data from a large ongoing experiment in forecasting world events.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Brier, G.W.: Verification of Forecasts Expressed in Terms of Probability. Monthly Weather Review 78(2) (1950)
Cencov, N.N.: Statistical Decision Rules and Optimal Inference. American Mathematical Society, Rhode Island (1982)
Forlines, C., Miller, S., Prakash, S., Irvine, J.: Heuristics for Improving Forecast Aggregation. In: Sun, W. (ed.) AAAI Fall Symposium 2012: Machine Aggregation of Human Judgment, Arlington, VA (2012)
Gescheider, G.A.: Psychophysics: The Fundamentals, 3rd edn. Psychology Press (1997)
Hong, L., Page, S.E.: Interpreted and Generated Signals. Journal of Economic Theory 144, 2174–2196 (2009)
Parunak, H.V.D.: Cluster-Weighted Aggregation. In: Sun, W. (ed.) AAAI Fall Symposium 2012: Machine Aggregation of Human Judgment, Arlington, Virginia (2012)
Parunak, H.V.D., Brueckner, S., Downs, L., Sappelsa, L.: Swarming Estimation of Realistic Mental Models. In: Electronic Proceedings, Thirteenth Workshop on Multi-Agent Based Simulation (MABS 2012 at AAMAS) (2012)
Parunak, H.V.D., Brueckner, S., Hong, L., Page, S.E., Rohwer, R.: Characterizing and Aggregating Agent Estimates. In: Ito, T., Jonker, C., Gini, M., Shehory, O. (eds.) Twelfth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2013). IFAAMAS, Minneapolis (2013)
Parunak, H.V.D., Downs, E.: Estimating Diversity among Forecaster Models. In: Sun, W. (ed.) AAAI Fall Symposium 2012: Machine Aggregation of Human Judgment, Arlington, Virginia (2012)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan-Kaufmann, San Francisco (1988)
Waterhouse, T.: Pay by the Bit: An Information-Theoretic Metric for Collective Human Judgment. In: Sun, W. (ed.) AAAI Fall Symposium 2012: Machine Aggregation of Human Judgment, Arlington, Virginia (2012)
Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bulletin 1(6), 80–83 (1945)
Zhu, H., Rohwer, R.: Measurements of Generalisation based on Information Geometry. In: Ellacott, S.W., Mason, J.C., Anderson, I.J. (eds.) Mathematics of Neural Networks: Models, Algorithms and Applications. Kluwer (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Van Dyke Parunak, H., Brueckner, S.A., Downs, E. (2013). Exploiting User Model Diversity in Forecast Aggregation. In: Greenberg, A.M., Kennedy, W.G., Bos, N.D. (eds) Social Computing, Behavioral-Cultural Modeling and Prediction. SBP 2013. Lecture Notes in Computer Science, vol 7812. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37210-0_56
Download citation
DOI: https://doi.org/10.1007/978-3-642-37210-0_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37209-4
Online ISBN: 978-3-642-37210-0
eBook Packages: Computer ScienceComputer Science (R0)