NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation

This study presents a machine learning-based approach to predicting the outcosmes of NBA games, with the aim of enhancing decision-making in sports betting and performance analysis. Using a dataset spanning 20 NBA seasons (2003–2023), we incorporated key features such as team statistics, player perf...

Full description

Saved in:
Bibliographic Details
Main Authors: Rodrigues F, Pires F
Format: Article
Language:English
Published: Sciendo 2025-05-01
Series:International Journal of Computer Science in Sport
Subjects:
Online Access:https://doi.org/10.2478/ijcss-2025-0006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271390714822656
author Rodrigues F
Pires F
author_facet Rodrigues F
Pires F
author_sort Rodrigues F
collection DOAJ
description This study presents a machine learning-based approach to predicting the outcosmes of NBA games, with the aim of enhancing decision-making in sports betting and performance analysis. Using a dataset spanning 20 NBA seasons (2003–2023), we incorporated key features such as team statistics, player performance metrics, and external factors like team fatigue and rankings. The methodology followed the CRISP-DM process, involving data preprocessing, feature selection, and model evaluation.
format Article
id doaj-art-9c5ee1a0ebaa4fb6b1c4b9cc66e1fa02
institution OA Journals
issn 1684-4769
language English
publishDate 2025-05-01
publisher Sciendo
record_format Article
series International Journal of Computer Science in Sport
spelling doaj-art-9c5ee1a0ebaa4fb6b1c4b9cc66e1fa022025-08-20T01:52:15ZengSciendoInternational Journal of Computer Science in Sport1684-47692025-05-012419411510.2478/ijcss-2025-0006NBA Results Forecast: From League Dynamics Analysis to Predictive Model ImplementationRodrigues F0Pires F1ISEP, Polytechnic of Porto, R. Dr. Aº Bernardino de Almeida, 431, Porto, 4249-015, Portugal.ISEP, Polytechnic of Porto, R. Dr. Aº Bernardino de Almeida, 431, Porto, 4249-015, Portugal.This study presents a machine learning-based approach to predicting the outcosmes of NBA games, with the aim of enhancing decision-making in sports betting and performance analysis. Using a dataset spanning 20 NBA seasons (2003–2023), we incorporated key features such as team statistics, player performance metrics, and external factors like team fatigue and rankings. The methodology followed the CRISP-DM process, involving data preprocessing, feature selection, and model evaluation.https://doi.org/10.2478/ijcss-2025-0006nbamachine learninggame outcome predictionfeature selectionclassification
spellingShingle Rodrigues F
Pires F
NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation
International Journal of Computer Science in Sport
nba
machine learning
game outcome prediction
feature selection
classification
title NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation
title_full NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation
title_fullStr NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation
title_full_unstemmed NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation
title_short NBA Results Forecast: From League Dynamics Analysis to Predictive Model Implementation
title_sort nba results forecast from league dynamics analysis to predictive model implementation
topic nba
machine learning
game outcome prediction
feature selection
classification
url https://doi.org/10.2478/ijcss-2025-0006
work_keys_str_mv AT rodriguesf nbaresultsforecastfromleaguedynamicsanalysistopredictivemodelimplementation
AT piresf nbaresultsforecastfromleaguedynamicsanalysistopredictivemodelimplementation