Open Access Open Access  Restricted Access Subscription or Fee Access

A Behaviorally Informed Survey-Powered Market Agent

Jessica Inchauspe, Pavel Atanasov, Barbara Mellers, Philip Tetlock, Lyle Ungar


We introduce a new method for converting individual probability estimates (obtained through surveys) into market orders for use in a Continuous Double Auction prediction market. Our Survey-Powered Market Agent (SPMA) algorithm is based on actual forecaster behavior, and offers notable advantages over existing market agent algorithms such as Zero Intelligence Plus (ZIP) agents: SPMAs only require probability estimates (and not bid direction nor quantity), are more behaviorally realistic, and work well when probabilities change over time. We validate SPMA using prediction market data and probability estimates elicited through surveys from a large set of forecasters on 88 individual forecasting problems over the course of a year. SPMA outperforms simple averages of the same probability forecasts and is competitive with sophisticated opinion poll aggregation methods and prediction markets. We use a rich set of market and poll data to empirically test the assumptions behind SPMA’s operation. In addition to aggregation efficiency, SPMA provides a framework for studying how forecasters convert probability estimates into trading orders, and offers a foundation for building hybrid markets which mix market traders and individuals producing independent probability estimates.


Automated Agents;Market Algorithm;Trading Agents

Full Text:



L R Anderson, C A Holt 'Information cascades and rational conformity' (2000) Encyclopedia of Cognitive Science.

J Armstrong and A Graefe 'Predicting elections from biographical information about candidates: A test of the index method' (2011) Journal of Business Research 64.7: 699-706.

P Atanasov e. a. 'The marketcast method for aggregating prediction market forecasts. In Social Computing, Behavioral-Cultural Modeling and Prediction' (2013) Springer, 28–37

A Augenblick and M Rabin 'A model-free test of excess volatility in beliefs streams' (2014) Under Review

J Baron, B Mellers, P Tetlock, E Stone, and L Ungar 'Two reasons to make aggregated probability forecasts more extreme'. (2014) Decision Analysis

J Berg, R Forsythe, F Nelson, T and Rietz 'Results from a dozen years of election futures markets research' (2001) Handbook of experimental economic results 1, 486–515.

G W Brier 'Verification of forecasts expressed in terms of probability' (1950) Monthly weather review 78, 1, 1–3.

D Cliff and J Bruten 'Zero is not enough: On the lower limit of agent intelligence for continuous double auction markets' (1997) HP Laboratories Tech. Report.

B Cowgill and E Zitzewitz 'Corporate prediction markets: Evidence from google, ford, and firm x' (2014) Under Review

S Gjerstad and M Hall 'Risk aversion, beliefs, and prediction market equilibrium' (2005) Economic Science Laboratory, University of Arizona.

D K Gode and S Sunder 'Allocative efficiency of markets with zero-intelligence traders: Market as a partial substitute for individual rationality' (1993) Journal of political economy 101, 1, 119

T S Gruca and J E Berg 'Public information bias and prediction market accuracy' (2012) The Journal of Prediction Markets 1, 3, 219–231

J L Kelly 'A new interpretation of information rate' (1956) Information Theory, IRE Transactions on 2, 3, 185–189.

C F Manski 'Interpreting the predictions of prediction markets' (2006) Economic Letters 91, 3, 425–429.

B Mellers e. a. 'Psychological strategies for winning a geopolitical forecasting tournament' (2014) Psychological science 0956797614524255.

M Ottaviani and P N Sørensen 'Aggregation of information and beliefs in prediction markets' (2007) In London Conference on Information and Prediction Markets

L Page and R T Clemen 'Do prediction markets produce well-calibrated probability forecasts?' (2013) The Economic Journal 123, 568, 491–513

V A Satopää̈ e. a. 'Combining multiple probability predictions using a simple logit model' (2014) International Journal of Forecasting 30, 2, 344–356

J Wolfers and E Zitzewitz 'Prediction markets' (2004) No. w10504. National Bureau of Economic Research

J Wolfers and E Zitzewitz 2006. 'Interpreting prediction market prices as probabilities' (2006) No. w12200. National Bureau of Economic Research



  • There are currently no refbacks.