Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 04024 | |
Number of page(s) | 6 | |
Section | AI and Advanced Applications | |
DOI | https://doi.org/10.1051/itmconf/20257004024 | |
Published online | 23 January 2025 |
Multiple Machine Learning Algorithms-based NBA Team Playoffs Prediction
Statistics and Data Science, University of California Santa Barbara, Santa Barbara, USA
Corresponding author: myeung@ucsb.edu
With the rapid development of data analytics in sports, it is vital to use machine learning methods to make decisions and predictions. This study focuses on predicting NBA playoff qualifications using machine learning techniques. By utilizing team-level statistics from 1947 to 2024, the paper implemented models such as Logistic Regression, K-Nearest Neighbors, Random Forest, and Elastic Net Regression. The data was preprocessed by scaling, centering, and handling missing values, followed by rigorous 5-fold cross-validation to ensure robust evaluation. Among the models, Random Forest outperformed the others, achieving the highest ROC-AUC score of 0.841. Its ensemble approach allowed for the effective capture of complex feature interactions, making it the most accurate model for predicting whether a team would qualify for the playoffs based on team performance. The research demonstrates the power of machine learning in improving prediction accuracy, providing insights for future sports analytics, and offering a foundation for integrating more complex data like player metrics or strategic factors. This work contributes to advancing predictive modeling in sports.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.