Tools
Tools
Panikkaveetil, Jaseem Jamal (2023) Ball Possession metrics-oriented Analysis to Predict Football League Rankings. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
The importance of ball possession from a strategic standpoint has drawn attention from coaches, analysts, and fans in modern football. This thesis offers a data-driven analysis of the importance of ball possession metrics for professional football league ranking prediction. By analysing the effects of adopting ball possession based game styles, the research seeks to show how possession-oriented strategies might help teams maximize their performance.
The algorithms used for the ranking predictions are XGBoost, LightGBM, Random Forest, Ridge Regression, and performance of all the models in predicting the goal count and possession is evaluated. The research studies the importance of ball possession metrics of both the home team and the away team in predicting the league rankings. Among the models, Random Forest model generated the lowest Mean Absolute Error values for home goal counts (0.0737), away goal counts (0.0974), and home possession (0.0289), away possession (0.0132). These results show the effectiveness of Random Forest in predicting football league rankings based on possession metrics.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Palaniswamy, Sasirekha UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports > Soccer Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 20 May 2025 12:55 |
| Last Modified: | 20 May 2025 12:55 |
| URI: | https://norma.ncirl.ie/id/eprint/7583 |
Actions (login required)
 |
View Item |