Football Match Prediction Using Information Markets
Prediction markets are used to predict the results of future events by gathering participants knowledge through market mechanisms. Various factors may affect market performance, such as the number of participants, participants knowledge, market duration, etc. Generally, it is believed that knowledgeable participants can predict the events more accurately than unknowledgeable participants. However, the information markets require adequate amount of participants regardless of their knowledge level. This research aims to study the impact of the number of participants and the participants knowledge level on the market accuracy. Participants are divided into two categories: knowledgeable participants and unknowledgeable participants. Experiments have been performed by opening 97 markets to predict football match results of English Premier League, Italy Serie A, Spain Primera Division, Germany Bundesliga I 2009/2010 and World Cup 2010. The results have shown that the larger number of participants in the prediction markets leads to the higher prediction accuracy. Confidence in the accuracy also improves with the number of participants. In addition, the number of knowledgeable participants is closely related to accuracy, while the number of unknowledgeable participants yields no significant relationship to the accuracy level.
Prediciton Markets Information Markets Knowledge
Pattarakit Watsanserekul Daricha Sutivong
Department of Industrial Engineering Faculty of Engineering, Chulalongkorn University Bangkok, Thailand
国际会议
2010 International Conference on Future Information Technology(2010年未来信息技术国际会议 ICFIT 2010)
长沙
英文
884-888
2010-12-14（万方平台首次上网日期，不代表论文的发表时间）