A Behaviorally Informed Survey-Powered Market Agent

2014 ◽  
Vol 8 (2) ◽  
pp. 1-28
Author(s):  
Jessica Inchauspe ◽  
Pavel Atanasov ◽  
Barbara Mellers ◽  
Philip Tetlock ◽  
Lyle Ungar
Keyword(s):  
Prediction Markets ◽  
Opinion Poll ◽  
Large Set ◽  
Prediction Market ◽  
Probability Estimates ◽  
Individual Probability ◽  
Continuous Double Auction ◽  
Zero Intelligence ◽  
Poll Data ◽  
Independent Probability

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.

IMPROVING FORECASTING ACCURACY IN CORPORATE PREDICTION MARKETS – A CASE STUDY IN THE AUSTRIAN MOBILE COMMUNICATION INDUSTRY

2012 ◽  
Vol 3 (3) ◽  
pp. 49-62
Author(s):  
Martin Waitz ◽  
Andreas Mild
Keyword(s):  
Predictive Ability ◽  
Market Mechanism ◽  
Prediction Markets ◽  
Data Sets ◽  
Success Rates ◽  
Prediction Market ◽  
Communication Industry ◽  
Market Participants ◽  
Market Shares ◽  
Continuous Double Auction

Corporate prediction markets forecast business issues like market shares, sales volumes or the success rates of new product developments. The improvement of its accuracy is a major topic in prediction market research. Mostly, such markets are using a continuous double auction market mechanism. We propose a method that aggregates the data provided by such a prediction market in a different way by only accounting for the most knowledgeable market participants. We demonstrate its predictive ability with a real world experiment.We want to thank Günter Fädler from pro:kons, an Austrian provider of prediction markets, for his support and providing us with the data sets used in this paper.

scholarly journals A study of efficiency in New Zealand election prediction markers

2021 ◽  
Author(s):  
◽  
Tram P. Cao
Keyword(s):  
Unit Root Test ◽  
Prediction Markets ◽  
Opinion Poll ◽  
Market Pricing ◽  
Market Prices ◽  
Arbitrage Opportunities ◽  
Election Prediction ◽  
Using Data ◽  
Abnormal Profits ◽  
Poll Data

<p>The development of prediction markets has naturally given rise to studies of their efficiency. Most studies of efficiency in prediction markets have focused on the speed with which they incorporate information. A necessary (but not sufficient) condition of efficiency is that arbitrage opportunities must non-existent or transitory in nature so that the systematic generation of abnormal profits is not possible. Using data from New Zealand’s first prediction market, iPredict, I examine the potential for arbitrage in the contracts for the party vote for the 2011 General Election. Relative to the risk-free interest rate, the returns from arbitrage are generally low, consistent with an efficient market. Regression analysis requires that the data not be subject to the possibility of spurious regressions - something that is not addressed in the literature. After confirming the non-stationarity of the price level and the stationarity of the price changes by the unit root test, I use the iPredict data in conjunction with opinion poll data to test whether the polls impact on market pricing behaviour. Using a number of different model types, I find that the opinion poll data has a very limited impact on market prices, suggesting that the information contained in the poll is largely already incorporated into market prices.</p>

scholarly journals A study of efficiency in New Zealand election prediction markers

2021 ◽  
Author(s):  
◽  
Tram P. Cao
Keyword(s):  
Unit Root Test ◽  
Prediction Markets ◽  
Opinion Poll ◽  
Market Pricing ◽  
Market Prices ◽  
Arbitrage Opportunities ◽  
Election Prediction ◽  
Using Data ◽  
Abnormal Profits ◽  
Poll Data

<p>The development of prediction markets has naturally given rise to studies of their efficiency. Most studies of efficiency in prediction markets have focused on the speed with which they incorporate information. A necessary (but not sufficient) condition of efficiency is that arbitrage opportunities must non-existent or transitory in nature so that the systematic generation of abnormal profits is not possible. Using data from New Zealand’s first prediction market, iPredict, I examine the potential for arbitrage in the contracts for the party vote for the 2011 General Election. Relative to the risk-free interest rate, the returns from arbitrage are generally low, consistent with an efficient market. Regression analysis requires that the data not be subject to the possibility of spurious regressions - something that is not addressed in the literature. After confirming the non-stationarity of the price level and the stationarity of the price changes by the unit root test, I use the iPredict data in conjunction with opinion poll data to test whether the polls impact on market pricing behaviour. Using a number of different model types, I find that the opinion poll data has a very limited impact on market prices, suggesting that the information contained in the poll is largely already incorporated into market prices.</p>

scholarly journals Prediction Markets for Crowdsourcing

2018 ◽  
Author(s):  
Christian Horn ◽  
Marcel Bogers ◽  
Alexander Brem*
Keyword(s):  
Stock Market ◽  
Open Innovation ◽  
Innovation Process ◽  
Business Practice ◽  
Prediction Markets ◽  
Knowledge Sources ◽  
Prediction Market ◽  
Online Platform ◽  
External Knowledge ◽  
Opening Up

Crowdsourcing is an increasingly important phenomenon that is fundamentally changing how companies create and capture value. There are still important questions with respect to how crowdsourcing works and can be applied in practice, especially in business practice. In this chapter, we focus on prediction markets as a mechanism and tool to tap into a crowd in the early stages of an innovation process. The act of opening up to external knowledge sources is also in line with the growing interest in open innovation. One example of a prediction market, a virtual stock market, is applied to open innovation through an online platform. We show that use of mechanisms of internal crowdsourcing with prediction markets can outperform use of external crowds.

Anomalies in Probability Estimates for Event Forecasting on Prediction Markets

2020 ◽  
Vol 29 (9) ◽  
pp. 2077-2095
Author(s):  
Ho Cheung Brian Lee ◽  
Jan Stallaert ◽  
Ming Fan
Keyword(s):  
Prediction Markets ◽  
Probability Estimates ◽  
Event Forecasting

A STATISTICAL MODEL OF CLAIM PRICES IN PREDICTION MARKETS

2012 ◽  
Vol 4 (3) ◽  
pp. 85-93
Author(s):  
Russ Ray
Keyword(s):  
Statistical Model ◽  
Financial Markets ◽  
Poisson Distribution ◽  
Prediction Markets ◽  
Inside Information ◽  
Prediction Market ◽  
The World ◽  
Global Agreement ◽  
High Degree

This paper finds that claim prices in prediction markets, a new genre of financial markets, follow a Poisson distribution. The significance of this finding is that as soon as a claim in a prediction market is created and thereafter flushes out expert and inside information from around the world regarding that particular claim, claim prices immediately begin forming bell-shaped distributions, implying global agreement regarding the probabilities of claims being realized. This is an interesting finding, implying a surprisingly high degree of global homogeneity of inside information in predictions markets, even though such information is scattered in disconnected and secretive pockets around the world. This finding could also imply that cultural diversities do not significantly affect the interpretation of information in prediction markets. 

Liquidity Provision and Cross Arbitrage in Continuous Double-Auction Prediction Markets

2014 ◽  
Vol 7 (3) ◽  
pp. 61-86
Author(s):  
Werner Antweiler
Keyword(s):  
Stock Market ◽  
Empirical Analysis ◽  
Double Auction ◽  
Prediction Markets ◽  
Market Maker ◽  
Micro Structure ◽  
Liquidity Provision ◽  
Novel Method ◽  
Continuous Double Auction ◽  
Bid Ask Spreads

Continuous double-auction prediction markets often exhibit low transaction volume due to substantial bid-ask spreads. This paper explores a novel method of providing artificial liquidity in continuous double-auction prediction markets by introducing an automated market maker that engages in zero-profit cross-arbitrage in multi-contract markets. Empirical analysis of observed bid-ask spreads, liquidity, offer acceptance, and order sizes in the 2008 UBC Election Stock Market provides additional new insights into the micro-structure of prediction markets. 

Evidencing the Forecasting Performance of Predication Markets: An Empirical Comparative Study

2018 ◽  
Vol 11 (2) ◽  
pp. 60-76
Author(s):  
Patrick Buckley
Keyword(s):  
Empirical Studies ◽  
Academic Research ◽  
Relevant Information ◽  
Prediction Markets ◽  
Problem Space ◽  
Prediction Market ◽  
Forecasting Performance ◽  
Planning Processes ◽  
Uncertain Outcomes ◽  
Aid Decision

Accurately forecasting uncertain outcomes to inform planning processes and aid decision making is a perennial organisational challenge, and the focus of a substantial body of research in management science, information systems and related disciplines. Academic research suggests that prediction markets may be of significant benefit to organisations in meeting this challenge. However most of the empirical studies assessing prediction market performance are laboratory based and suffer from limits to their generalizability. Recent literature has called for research which analyses the performance of prediction markets in ecologically valid settings in order to evidence their effectiveness to potential organisational users. This paper answers these calls by designing a prediction market to forecast an uncertain real world event. The study then compares the forecasting performance of the prediction market with a number of more traditional forecasting approaches regularly used by organisations. The study is contextually situated in a low information heterogeneity problem space, where relevant information is freely available. The results suggest that in this context prediction markets outperform the other forecasting methods studied.

PRIVATE PREDICTION MARKETS AND THE LAW

2012 ◽  
Vol 3 (1) ◽  
pp. 89-110 ◽  
Author(s):  
Tom Bell
Keyword(s):  
Prediction Markets ◽  
Management Decisions ◽  
Prediction Market ◽  
The Public ◽  
Legal Risks ◽  
Federal Laws ◽  
The Law ◽  
Considerable Benefit

This paper analyses the legality of private prediction markets under U.S. law, describing both the legal risks they raise and how to manage those risks.  As the label "private" suggests, such markets offer trading not to the public but rather only to members of a particular firm.  The use of private prediction markets has grown in recent years because they can efficiently collect and quantify information that firms find useful in making management decisions.  Along with that considerable benefit, however, comes a worrisome cost:  the risk that running a private prediction market might violate U.S. state or federal laws.  The ends and means of private prediction markets differ materially from those of futures, securities, or gambling markets.  Laws written for those latter three institutions nonetheless threaten to limit or even outlaw private prediction markets.  As the paper details, however, careful legal engineering can protect private prediction markets from violating U.S. laws or suffering crushing regulatory burdens.  The paper concludes with a prediction about the likely form of potential CFTC regulations and a long-term strategy for ensuring the success of private prediction markets under U.S. law.

Sign in / Sign up

Export Citation Format

Share Document