Predicting the Performance of Bowlers in IPL: An Application of Artificial Neural Network

Abstract

Application of data mining tools is often used in professional sports for evaluating players/teams’ performance. Cricket is one of those sports where a large amount of numerical information is generated in every game. The game of cricket got a new dimension in April 2008, when Board of Control for Cricket in India (BCCI) initiated the Indian Premier League(IPL). It is a franchise based Twenty20 cricket tournament where teams are formed by competitive bidding from a collection of Indian and International players. Since, valuations of the players are determined through auction, so performance of individual player is always under scanner. The objective of this study is to analyze and predict the performance of bowlers in IPL, using artificial neural network. Based on the performance of bowlers in the first three seasons of IPL, the paper tries to predict the performances of those bowlers who entered in the league in its fourth season as their maiden IPL venture. The performances of these bowlers in IPL-IV are predicted, and the external validity of the model is tested using their actual performance in IPL-IV. This prediction can help the franchises to decide which bowler they should target for their team.