Cricket Shot Prediction using Match Context Data by use of XGBoost Classifier

Shirke, Megh Vijay (2025) Cricket Shot Prediction using Match Context Data by use of XGBoost Classifier. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (769kB) | Preview

Abstract

A newer and popular use of sports analytics has been in batting shot prediction, namely in the context of cricket where real-time decision support can be applied to improve coaching, broadcast analysis and performance evaluation. In this paper, we build a machine-learning model that can predict the type of shot of a batsman based on the ball-by-ball data, but with context information of Fatigue Index and Match Situation Index. Textual descriptions consisting of commentaries are transformed with the help of a TF-IDF vectorisation, whereas categorical and numerical variables are coded with the help of One-Hot Encoding and normalised inputs. The imbalance between the classes, especially when it comes to uncommon shots like the hook, was handled with the help of SMOTE. A trained and tested XGBoost model was found to have a 95 percent accuracy and a weighted F1-score of 0.95. The findings reveal that the predictive validity of most of the shot types is high, and the consequences of the contextual game pressure and fatigue on the selection of the shot. The present study offers a solid foundation of cricket analytics and creates opportunities of the real-time predictive analytics and fatigue-conscious performance modelling.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Razzaq, Muhammad Asif UNSPECIFIED
Uncontrolled Keywords:	Shot Predection; Cover Drive; Prediction pipeline; Cricket; NLP; Text Vectorisation; Machine Learning; Match Context
Subjects:	P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	09 Sep 2026 09:36
Last Modified:	09 Sep 2026 09:36
URI:	https://norma.ncirl.ie/id/eprint/9913

Actions (login required)

View Item