Improving prediction market forecasts by detecting and correcting possible over-reaction to price movements
Improving prediction market forecasts by detecting and correcting possible over-reaction to price movements
We examine the impact of price trends on the accuracy of forecasts from prediction markets. In particular, we study an electronic betting exchange market and construct independent variables from market price (odds) time series from 6,058 individual markets (a dataset consisting of over 8.4 million price points). Using a conditional logit model, we find that a systematic relationship exists between trends in odds and the accuracy of odds-implied event probabilities; the relationship is consistent with participants over-reacting to price movements. In particular, in different time segments of the market, increasing and decreasing odds lead, respectively, to under- and over-estimation of odds-implied probabilities. We develop a methodology to detect and correct the erroneous forecasts associated with these trends in odds in order to considerably improve the quality of forecasts generated in prediction markets.
389-405
Sung, Ming-Chien
2114f823-bc7f-4306-a775-67aee413aa03
Mcdonald, David C.J.
fbe07af1-0891-4db7-858c-793633d98f3f
Johnson, Johnnie
6d9f1a51-38a8-4011-a792-bfc82040fac4
Tai, Chung-Ching
b3370b23-7410-4254-99bc-6711046e1095
Cheah, Eng-Tuck
298800de-521f-4aa8-9c04-2f58eece4c6e
1 January 2019
Sung, Ming-Chien
2114f823-bc7f-4306-a775-67aee413aa03
Mcdonald, David C.J.
fbe07af1-0891-4db7-858c-793633d98f3f
Johnson, Johnnie
6d9f1a51-38a8-4011-a792-bfc82040fac4
Tai, Chung-Ching
b3370b23-7410-4254-99bc-6711046e1095
Cheah, Eng-Tuck
298800de-521f-4aa8-9c04-2f58eece4c6e
Sung, Ming-Chien, Mcdonald, David C.J., Johnson, Johnnie, Tai, Chung-Ching and Cheah, Eng-Tuck
(2019)
Improving prediction market forecasts by detecting and correcting possible over-reaction to price movements.
European Journal of Operational Research, 272 (1), .
(doi:10.1016/j.ejor.2018.06.024).
Abstract
We examine the impact of price trends on the accuracy of forecasts from prediction markets. In particular, we study an electronic betting exchange market and construct independent variables from market price (odds) time series from 6,058 individual markets (a dataset consisting of over 8.4 million price points). Using a conditional logit model, we find that a systematic relationship exists between trends in odds and the accuracy of odds-implied event probabilities; the relationship is consistent with participants over-reacting to price movements. In particular, in different time segments of the market, increasing and decreasing odds lead, respectively, to under- and over-estimation of odds-implied probabilities. We develop a methodology to detect and correct the erroneous forecasts associated with these trends in odds in order to considerably improve the quality of forecasts generated in prediction markets.
Text
1-s2.0-S0377221718305575-main
- Accepted Manuscript
Text
Manuscript no highlight_
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 11 June 2018
e-pub ahead of print date: 20 June 2018
Published date: 1 January 2019
Identifiers
Local EPrints ID: 421405
URI: http://eprints.soton.ac.uk/id/eprint/421405
ISSN: 0377-2217
PURE UUID: ee28a072-3c86-4d78-a708-214b0708606e
Catalogue record
Date deposited: 11 Jun 2018 16:30
Last modified: 16 Mar 2024 06:44
Export record
Altmetrics
Contributors
Author:
David C.J. Mcdonald
Author:
Johnnie Johnson
Author:
Eng-Tuck Cheah
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics