Citation

Ibrahim, Siti Zainab and Reza, Aditya Muhammad and Kean, Lew Wei and Ab Aziz, Nor Azlina and Sayed Ismail, Sharifah Noor Masidayu (2024) Machine Learning Insights into Basketball Championship Predictions: An Analytical Comparison. In: International Conference on Innovation and Technology in Sports, 26-27 Nov 2023, Malaysia.

Full text not available from this repository.

Abstract

Leveraging machine learning techniques to forecast the eventual championship-winning teams through the consideration of diverse sport-related variables has garnered substantial attention in contemporary sports research. In this study, the focus resides in employing machine learning models to forecast National Basketball Association (NBA) champions. The techniques were applied to a selected NBA dataset originated from data.world. Central to this endeavor is the role of feature selection which proves pivotal not only in discerning NBA championships but also in gauging predictive capacities. Five machine learning models encompassing Decision Trees, Random Forests, Logistic Regression, Support Vector Machines (SVMs), and Autoencoders were employed to offer multifaceted insights into the projection of victorious teams and their performance trajectories. Each model exhibited varying degrees of predictive accuracy. The autoencoders model emerged as the pinnacle performer by attaining the highest accuracy levels of 0.888 and 0.810. The findings provided exciting insights into determining the NBA championship and demonstrating the roles of machine learning in predicting championships. This study demonstrates the potential application of machine learning across a wide range of sports arenas. It aspires to foster advancements in predictive analytics thereby enhancing the precision of such forecasts and their broad applicability.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine learning, sport
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	02 Sep 2024 09:04
Last Modified:	02 Sep 2024 09:04
URII:	http://shdl.mmu.edu.my/id/eprint/12935

Downloads

Edit (login required)