Tools
Tools
Bajaj, Ayushi (2023) Prediction of Player Performance for IPL and analysing the attributes involved, using Explainable AI. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Cricket is the second most popular game across the globe. It is played in numerous formats but the most fast paced format is called T20 which has twenty overs. With the increase in its popularity the game has is been played in T20 format in various leagues. The most popular among all these leagues is Indian Premier League. A lot of money is involved in this league hence player selection becomes an important part of the game. As scores of cricket has high numerical influence computational analysis proves to very beneficial for prediction related to it. This paper provides the findings for optimal player selection and identifying the impact of features using Explainable Artificial Intelligence.The player has two primary roles in the game batting and bowling the secondary role involve fielding and wicket keeping. The paper analyses every player’s performance in terms of total points and regression models are used to predict these performances in IPL. The models used are Random Forest, Decision tree, SVM and XGBoost. Then these models are compared based on RMSE score where XGBoost provides the most promising results. Later hyperparameter optimization is applied on XGBoost model using optuna which provides even more accurate results. Lastly, Explainable AI is performed using SHAP library to understand the role of factors affecting the predictions.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Anant, Aaloka UNSPECIFIED |
| Uncontrolled Keywords: | Cricket; IPL; XGBoost; Decision Tree; SVR; Random Forest; Explainable AI |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 17 May 2023 09:56 |
| Last Modified: | 17 May 2023 09:56 |
| URI: | https://norma.ncirl.ie/id/eprint/6564 |
Actions (login required)
 |
View Item |