Forecasting Most Valuable Players of the National Basketball Association

Search for this publication on Google Scholar
McCorey, J. (2021). Forecasting Most Valuable Players of the National Basketball Association. Unc Charlotte Electronic Theses And Dissertations.
Download PDF

Analytics

240 views ◎
197 downloads ⇓


Abstract

This thesis aims at developing models that would accurately forecast the Most Valuable Player (MVP) of the National Basketball Association (NBA). R programming language was used in this study to implement different techniques, such as Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), and Linear Regression Models (LRM). NBA statistics were extracted from all of the past MVP recipients and the top five runner-up MVP candidates from the last ten seasons (2009-2019). The objective is to forecast the Point Total Ratio (PTR) for MVP during the regular season. Seven different underlying models were created and applied to the three techniques in order to produce potential outputs for the 2018-19 season. The best models were then selected and optimized to form the MVP forecasting algorithm, which was validated by predicting the MVP of the 2019-20 season. Ultimately, two underlying models were most robust under the LRM framework, which is considered the champion approach. As a result, two combination models were constructed based on the champion approach and proved to be most efficient. The two finalized combination models then served as the forecasting algorithm used to predict players PTR. Using this algorithm, one of the top players in PTR will win the MVP award for the regular season of the NBA. Hence, this proposed algorithm can be used post All-Star selections to determine the Most Valuable Player.

Details
Author

McCorey, Jordan

Title

Forecasting Most Valuable Players of the National Basketball Association

Physical Description

1 online resource (104 pages) : PDF

Date

2021

Degree Granting Institution

University of North Carolina at Charlotte

Abstract

This thesis aims at developing models that would accurately forecast the Most Valuable Player (MVP) of the National Basketball Association (NBA). R programming language was used in this study to implement different techniques, such as Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), and Linear Regression Models (LRM). NBA statistics were extracted from all of the past MVP recipients and the top five runner-up MVP candidates from the last ten seasons (2009-2019). The objective is to forecast the Point Total Ratio (PTR) for MVP during the regular season. Seven different underlying models were created and applied to the three techniques in order to produce potential outputs for the 2018-19 season. The best models were then selected and optimized to form the MVP forecasting algorithm, which was validated by predicting the MVP of the 2019-20 season. Ultimately, two underlying models were most robust under the LRM framework, which is considered the champion approach. As a result, two combination models were constructed based on the champion approach and proved to be most efficient. The two finalized combination models then served as the forecasting algorithm used to predict players PTR. Using this algorithm, one of the top players in PTR will win the MVP award for the regular season of the NBA. Hence, this proposed algorithm can be used post All-Star selections to determine the Most Valuable Player.

Genre

masters theses

Subjects--Topics

Engineering
Industrial engineering

Degree

M.S.

Keywords

Algorithm
Analytics
Basketball
Coding
Forecasting
Sports

Subject Area

Engineering Management

Advisor(s)

Hong, Tao

Committee Members

Bai, Linquan
Wang, Pu

Degree Note

Thesis (M.S.)--University of North Carolina at Charlotte, 2021.

Rights Statement

This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). For additional information, see http://rightsstatements.org/page/InC/1.0/.

Rights Holder Information

Copyright is held by the author unless otherwise indicated.

Identifier

McCorey_uncc_0694N_12828

Permalink

http://hdl.handle.net/20.500.13093/etd:2482