As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Neural networks have been widely used in artificial intelligence over the last ten years. They attract a lot of attention recently because of their ability to generalize and respond to unexpected inputs and patterns. This study is an extension of my previous study, in which NBA offensive and defensive statistics was analyzed, and a multiple linear regression model was built to predict NBA teams’ winning percentages. The objective of this study is to apply neural network algorithms to predict NBA team records, and to compare the results with regression models. In this study, the neural network modes has a better prediction accuracy than the linear regression models. This is likely due to neural networks being able to handle non-linear parameters while also implementing ensemble learning.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.