Predicting Results of Indian Premier League T-20 Matches using Machine Learning

Cricket, the most exciting and fascinating game that the people of all age group are very crazy to see and play. It is considered to be the most interesting and uncertain game. For many it becomes a billion dollar market as they speculate financially, hope of being able to earn profit. Every year the gambling market is going to be on hike as there is much great concern about spot fixing. In this paper, we have studied the problem of predicting the uncertainty of who will win the upcoming IPL match based on the individual competency of each player, coordination and team work of whole team evolving and technique followed by each team in each match. In this paper we propose a model using machine learning algorithms that can predict winning team based on past data available. We applied three machine learning algorithms namely Support Vector Machine, CTree and Naïve Bayes and achieved an accuracy of 95.96%, 97.98% and 98.99% respectively.

Paper

Full text

PDF

Predicting Results of Indian Premier League T-20 Matches using Machine Learning

Semantic Scholar · Computer Science · 2018

Abstract

Cricket, the most exciting and fascinating game that the people of all age group are very crazy to see and play. It is considered to be the most interesting and uncertain game. For many it becomes a billion dollar market as they speculate financially, hope of being able to earn profit. Every year the gambling market is going to be on hike as there is much great concern about spot fixing. In this paper, we have studied the problem of predicting the uncertainty of who will win the upcoming IPL match based on the individual competency of each player, coordination and team work of whole team evolving and technique followed by each team in each match. In this paper we propose a model using machine learning algorithms that can predict winning team based on past data available. We applied three machine learning algorithms namely Support Vector Machine, CTree and Naïve Bayes and achieved an accuracy of 95.96%, 97.98% and 98.99% respectively.

Similar papers

© 2026 NYSGPT2525 LLC