Stacked ensemble model for NBA game outcome prediction analysis

Abstract This research presents a stacked ensemble approach that employs artificial intelligence (AI) techniques to predict the outcomes of NBA games. Several machine learning algorithms were utilized, including Naïve Bayes, AdaBoost, Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), XGBoost,...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangsen He, Hyun Soo Choi
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-13657-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736286933352448
author Guangsen He
Hyun Soo Choi
author_facet Guangsen He
Hyun Soo Choi
author_sort Guangsen He
collection DOAJ
description Abstract This research presents a stacked ensemble approach that employs artificial intelligence (AI) techniques to predict the outcomes of NBA games. Several machine learning algorithms were utilized, including Naïve Bayes, AdaBoost, Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), XGBoost, Decision Tree, and Logistic Regression. The best-performing models were selected to serve as the base learners in the ensemble architecture. To improve the model’s interpretability and transparency, SHAP was used to clarify its decision-making process. The model was trained and evaluated using publicly available NBA datasets from 2021–2022,2022–2023, and 2023–2024. Experimental results indicate that the proposed ensemble approach is practical in predicting game outcomes. Furthermore, the SHAP analysis provides valuable insights into the underlying predictive mechanisms, offering actionable information for coaches and analysts.
format Article
id doaj-art-011e3e3702cf4910a08ce410f86f00a8
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-011e3e3702cf4910a08ce410f86f00a82025-08-20T03:07:20ZengNature PortfolioScientific Reports2045-23222025-08-0115111710.1038/s41598-025-13657-1Stacked ensemble model for NBA game outcome prediction analysisGuangsen He0Hyun Soo Choi1Department of Physical Education, Hanyang UniversityDepartment of Physical Education, Hanyang UniversityAbstract This research presents a stacked ensemble approach that employs artificial intelligence (AI) techniques to predict the outcomes of NBA games. Several machine learning algorithms were utilized, including Naïve Bayes, AdaBoost, Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), XGBoost, Decision Tree, and Logistic Regression. The best-performing models were selected to serve as the base learners in the ensemble architecture. To improve the model’s interpretability and transparency, SHAP was used to clarify its decision-making process. The model was trained and evaluated using publicly available NBA datasets from 2021–2022,2022–2023, and 2023–2024. Experimental results indicate that the proposed ensemble approach is practical in predicting game outcomes. Furthermore, the SHAP analysis provides valuable insights into the underlying predictive mechanisms, offering actionable information for coaches and analysts.https://doi.org/10.1038/s41598-025-13657-1Machine learningStacked ensembleShapley additive explanation (SHAP)Features selectionData mining
spellingShingle Guangsen He
Hyun Soo Choi
Stacked ensemble model for NBA game outcome prediction analysis
Scientific Reports
Machine learning
Stacked ensemble
Shapley additive explanation (SHAP)
Features selection
Data mining
title Stacked ensemble model for NBA game outcome prediction analysis
title_full Stacked ensemble model for NBA game outcome prediction analysis
title_fullStr Stacked ensemble model for NBA game outcome prediction analysis
title_full_unstemmed Stacked ensemble model for NBA game outcome prediction analysis
title_short Stacked ensemble model for NBA game outcome prediction analysis
title_sort stacked ensemble model for nba game outcome prediction analysis
topic Machine learning
Stacked ensemble
Shapley additive explanation (SHAP)
Features selection
Data mining
url https://doi.org/10.1038/s41598-025-13657-1
work_keys_str_mv AT guangsenhe stackedensemblemodelfornbagameoutcomepredictionanalysis
AT hyunsoochoi stackedensemblemodelfornbagameoutcomepredictionanalysis