Abstract
Two models are used to predict the outcomes of matches in a Twenty20 cricket series. The success of prediction methods is hampered by the fact that if two teams play two or more matches against each other and each team wins some of the matches, such inconsistent outcomes cannot all be predicted correctly. The challenge was to find a procedure which could compensate for inconsistent results. The consistency adjusted measure of the success of prediction is defined and shown to give a fair assessment of prediction results. For the first model the success rate of 56.8% is increased to 76.4% and for the second model from 52.7% to 70.9%. The same method can be used in any sports series where teams play against each other more than once.
Get full access to this article
View all access options for this article.
