Prediction of Cricket Players Performance Using Machine Learning

In any sport, especially in cricket selection of the players is the most significant job of the team management. The efficiency of a player depends on various circumstances such as experience, current form, performance in the previous match, as well as performance at the specific venue, etc. The cricket board appoints selectors, they sit along with the captain and decide the merit of each top performer and can select any 11 players for each match of the series from a squad of 15–20 players. The coach provides suggestions and helps the captain in making decisions. We experiment to predict the performance of the players by considering their ratings such as batting or bowling averages, respectively. These problems are indicated as classification problems where number of runs and number of wickets are classified in different ranges. Moreover in this paper, we used relevant scoring factor, co-efficient correlation and tree classifiers to generate the prediction models for these problems.