On predicting an NBA game outcome from half-time statistics

Abstract Predicting the outcome of an NBA game is a major concern for betting companies and individuals who are willing to bet. We attack this task by employing various advanced machine learning algorithms and techniques, utilizing simple half-time statistics from both teams. Data collected from 3 s...

Full description

Saved in:
Bibliographic Details
Main Authors: Michail Tsagris, Christos Adam, Pavlos Pantatosakis
Format: Article
Language:English
Published: Springer 2024-12-01
Series:Discover Artificial Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44163-024-00201-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846112440974049280
author Michail Tsagris
Christos Adam
Pavlos Pantatosakis
author_facet Michail Tsagris
Christos Adam
Pavlos Pantatosakis
author_sort Michail Tsagris
collection DOAJ
description Abstract Predicting the outcome of an NBA game is a major concern for betting companies and individuals who are willing to bet. We attack this task by employing various advanced machine learning algorithms and techniques, utilizing simple half-time statistics from both teams. Data collected from 3 seasons, from 2020/21 up to 2022/23 were used to assess the predictive performance of the algorithms at two axes. For each season separately, apply the algorithms and estimate the outcomes of the games of the same season and secondly, apply the algorithms in one season and estimate the outcomes of the games in the next season. The results showed high levels of accuracy as measured by the area under the curve. The analysis was repeated after performing variable selection using a non-linear algorithm that selected the most important half-time statistics, while retaining the predictive performance at high levels of accuracy.
format Article
id doaj-art-cc41e46aaf474ab486da273e52c5597e
institution Kabale University
issn 2731-0809
language English
publishDate 2024-12-01
publisher Springer
record_format Article
series Discover Artificial Intelligence
spelling doaj-art-cc41e46aaf474ab486da273e52c5597e2024-12-22T12:36:33ZengSpringerDiscover Artificial Intelligence2731-08092024-12-014112310.1007/s44163-024-00201-9On predicting an NBA game outcome from half-time statisticsMichail Tsagris0Christos Adam1Pavlos Pantatosakis2University of CreteUniversity of CreteUniversity of CreteAbstract Predicting the outcome of an NBA game is a major concern for betting companies and individuals who are willing to bet. We attack this task by employing various advanced machine learning algorithms and techniques, utilizing simple half-time statistics from both teams. Data collected from 3 seasons, from 2020/21 up to 2022/23 were used to assess the predictive performance of the algorithms at two axes. For each season separately, apply the algorithms and estimate the outcomes of the games of the same season and secondly, apply the algorithms in one season and estimate the outcomes of the games in the next season. The results showed high levels of accuracy as measured by the area under the curve. The analysis was repeated after performing variable selection using a non-linear algorithm that selected the most important half-time statistics, while retaining the predictive performance at high levels of accuracy.https://doi.org/10.1007/s44163-024-00201-9NBAHalf-time statisticsGame outcomeMachine learning
spellingShingle Michail Tsagris
Christos Adam
Pavlos Pantatosakis
On predicting an NBA game outcome from half-time statistics
Discover Artificial Intelligence
NBA
Half-time statistics
Game outcome
Machine learning
title On predicting an NBA game outcome from half-time statistics
title_full On predicting an NBA game outcome from half-time statistics
title_fullStr On predicting an NBA game outcome from half-time statistics
title_full_unstemmed On predicting an NBA game outcome from half-time statistics
title_short On predicting an NBA game outcome from half-time statistics
title_sort on predicting an nba game outcome from half time statistics
topic NBA
Half-time statistics
Game outcome
Machine learning
url https://doi.org/10.1007/s44163-024-00201-9
work_keys_str_mv AT michailtsagris onpredictingannbagameoutcomefromhalftimestatistics
AT christosadam onpredictingannbagameoutcomefromhalftimestatistics
AT pavlospantatosakis onpredictingannbagameoutcomefromhalftimestatistics