A comparative study of cricket par score using Machine Learning and DL method

Tawade, Omkar (2021) A comparative study of cricket par score using Machine Learning and DL method. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

Cricket has become popular with the advent of the T20 format, the shortest format of the game. Like other games, the outcome of a cricket match is also essential, but sometimes rain plays a spoilsport in this game. The current rain rule method, the Duckworth Lewis method, is used to calculate the revised score. Duckworth Lewis method invented for one-day international cricket is now used in T20 cricket by just scaling down the resource table could be contentious. This research aims to develop models based on a machine-learning algorithm to predict the score of rain-interrupted matches. The Indian premier league (2008-2020) dataset from Kaggle is used for the purpose of the study. This research introduced novel features, including runs, wickets, dot balls, and the number of boundaries scored in the last five overs. Extreme gradient boosting (XGBoost), Adaptive Boosting (AdaBoost) and Random forest algorithms are used in the research to produce models. Results showed that the proposed method successfully predicted scores with less margin of error when compared to the Duckworth Lewis method. Experiments showed that models based on second innings data provided better results in terms of RMSE and MAE.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	15 Dec 2021 10:22
Last Modified:	15 Dec 2021 10:22
URI:	https://norma.ncirl.ie/id/eprint/5229

Actions (login required)

View Item