Date of Award
5-2024
Document Type
Thesis
Degree Name
Master of Science
Degree Discipline
Computer Science
Abstract
In the dynamic realm of NBA team management, balancing the intricacies of player performance and strategic signings present formidable challenges. Negotiating salary caps, player roles, on-court minutes, and contract durations requires a nuanced approach. This study comprehensively evaluated player efficiency and team performance, scrutinizing key statistical indicators like Points, Rebounds, Assists, Blocks, PER, RPM, Shot Charts, and others. Leveraging machine learning algorithms, including logistic, ridge, and lasso regressions, facilitated modeling the intricate relationship between player performance and team winning rates. Based on that, incorporating practical constraints yielded diverse and effective teaming strategies. Analyzing NBA player and game statistics from 2012 to 2022, the experimental findings underscore the accuracy of prediction models and the success of player selection strategies. This research provides actionable insights for NBA franchises seeking to streamline team operations and achieve triumphs on the court.
Index Terms: Court coverage, machine learning, NBA, performance evaluation, shot charts, sports analysis, teaming strategy.
Committee Chair/Advisor
Lin Li
Committee Co-Chair
Yonghui Wang
Committee Member
Sherri S. Frizell
Committee Member
Na Li
Publisher
Prairie View A&M University
Rights
© 2021 Prairie View A & M University
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Date of Digitization
6/6/2024
Contributing Institution
John B Coleman Library
City of Publication
Prairie View
MIME Type
Application/PDF
Recommended Citation
Siddique, S. (2024). Teaming Strategy Optimization: An Analysis Of NBA Statistics, Shot Charts, And Constraints. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/1535