Prediction on basketball team-rankings in CBA using past stats with weighted linear regression

Xiwen Zhang; Juiwei Lee; Yuanzheng Yu; Chenglin Lu

doi:10.1117/12.3031261

19 July 2024 Prediction on basketball team-rankings in CBA using past stats with weighted linear regression

Xiwen Zhang, Juiwei Lee, Yuanzheng Yu, Chenglin Lu

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 1318162 (2024) https://doi.org/10.1117/12.3031261
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

This study examines the application of weighted linear regression in predicting the team standings in Chinese Basketball Association (CBA) at the end of a regular season. Using historical game stats from 2017-2022 as training set, a linear regression model has been developed to predict the outcomes of CBA regular season based on the average performance of each team, which includes 20 features in the box score. The result of the analysis indicates that the weighted linear regression model is capable of make predictions of the team rankings with an accuracy of 61.4%. While key features like points/rebounds/assists per game got considered with different positive weights, unfavorable features like turnovers and personal fouls are considered to have negative weights. The findings of this research have practical implications for CBA and other sports leagues that aren't as well studied as the NBA. The predictions of league rankings indicate the winning probability and strength of the teams, which could be referenced by fans, coaches, team officials, and even gamblers. Furthermore, the methodology discussed in this paper can be extended to other statistically recorded sports and other sports with stats records and other domains where predictive modeling is possible. Overall, the effectiveness of weighted linear regression model in predicting the outcomes of games in unpopular basketball leagues like CBA has been proved valid through this research; and the unlimited potential of machine learning in the real world has been underlined.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiwen Zhang, Juiwei Lee, Yuanzheng Yu, and Chenglin Lu "Prediction on basketball team-rankings in CBA using past stats with weighted linear regression", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 1318162 (19 July 2024); https://doi.org/10.1117/12.3031261

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Linear regression

Data modeling

Performance modeling

Education and training

Machine learning

Random forests

Deep learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years