Estimating the Chances of Winning IPL Match using Machine Learning

Abstract

Cricket is a popular sport not only in India but across the world. In recent years, the T-20 variant of this game has become extremely popular. The Indian Premier League (IPL), one of the championships associated with this format, has grown rapidly. On the other hand, cricket has long been considered a high-risk sport. Predicting the winner of the tournament or the game has an area of concern for many fans. Innovation, on the other hand, is progressing at an alarming rate. For model training, researchers always turn to machine learning (ML) algorithms to predict something. In this study, we will predict the probable percentage of winning of team in the IPL using different supervised learning methods. To predict our outcomes, we will apply the Logistic Regression (LR) Algorithm in this work. The existing models were trying to predict the match result before the start of the match which leads to automatic less accuracy. But, the proposed model is more effective because it predicts match winning percentage in the second inning that was not done earlier. In comparison to other existing algorithms, the proposed LR algorithm has an accuracy of 80%.