Predicting Outcome of Indian Premier League (IPL) Matches Using Classification Based Machine Learning Algorithm
share
Cricket, especially the twenty20 format, has maximum uncertainty, where a single over can completely change the momentum of the game. With millions of people following the Indian Premier League, therefore developing a model for predicting the outcome of its matches beforehand is a real-world problem. A cricket match depends upon various factors, and in this work various feature selection methods were used to reduce the number of features to 5 from 15. Player's performance in the field is considered to find out the relative strength of the team. A Linear Regression based solution is proposed to calculate the weightage of a team based on the past performance of its players who have appeared most for the team. Finally, a dataset with the features: home team, away team, stadium, toss winner, toss decision, home team weightage and away team weightage, is fed to a Random Forest Classifier to train the model and make prediction on unseen matches. Classification results are satisfactory. Problem in the dataset and how the accuracy of the classifier can be improved is discussed.
READ FULL TEXT
