Machine learning and the NBA Game

Bojan Georgievski; Sabahudin Vrtagic

doi:10.7752/jpes.2021.06453

Machine learning and the NBA Game

Bojan Georgievski^*, Sabahudin Vrtagic

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

4 Citations (Scopus)

Abstract

The purpose of this research was to analyse changes in performance through data simulation. Machine learning has been a popular tool for prediction in the NBA. What we wanted to see how a change in performance is affected in actual points. When a club improves its game, or when a club underperforms what that means as points. Through a points-prediction simulation, we analysed how a change in performance of 1–3% will affect the top five–performing and worst performing clubs.

Original language	English
Article number	453
Pages (from-to)	3339-3343
Number of pages	5
Journal	Journal of Physical Education and Sport
Volume	21
Issue number	6
DOIs	https://doi.org/10.7752/jpes.2021.06453
Publication status	Published - Dec 2021
Externally published	Yes

Keywords

Back propagation
Modelling or simulation performance drop coefficients
NBA basketball
Offensive and defensive data simulation

Access to Document

10.7752/jpes.2021.06453

Cite this

@article{e95f12756f9144d3ad3efcbe6aeb7326,

title = "Machine learning and the NBA Game",

abstract = "The purpose of this research was to analyse changes in performance through data simulation. Machine learning has been a popular tool for prediction in the NBA. What we wanted to see how a change in performance is affected in actual points. When a club improves its game, or when a club underperforms what that means as points. Through a points-prediction simulation, we analysed how a change in performance of 1–3% will affect the top five–performing and worst performing clubs.",

keywords = "Back propagation, Modelling or simulation performance drop coefficients, NBA basketball, Offensive and defensive data simulation",

author = "Bojan Georgievski and Sabahudin Vrtagic",

note = "Publisher Copyright: {\textcopyright} JPES.",

year = "2021",

month = dec,

doi = "10.7752/jpes.2021.06453",

language = "English",

volume = "21",

pages = "3339--3343",

journal = "Journal of Physical Education and Sport",

issn = "2247-8051",

publisher = "Editura Universitatii din Pitesti",

number = "6",

}

TY - JOUR

T1 - Machine learning and the NBA Game

AU - Georgievski, Bojan

AU - Vrtagic, Sabahudin

N1 - Publisher Copyright: © JPES.

PY - 2021/12

Y1 - 2021/12

N2 - The purpose of this research was to analyse changes in performance through data simulation. Machine learning has been a popular tool for prediction in the NBA. What we wanted to see how a change in performance is affected in actual points. When a club improves its game, or when a club underperforms what that means as points. Through a points-prediction simulation, we analysed how a change in performance of 1–3% will affect the top five–performing and worst performing clubs.

AB - The purpose of this research was to analyse changes in performance through data simulation. Machine learning has been a popular tool for prediction in the NBA. What we wanted to see how a change in performance is affected in actual points. When a club improves its game, or when a club underperforms what that means as points. Through a points-prediction simulation, we analysed how a change in performance of 1–3% will affect the top five–performing and worst performing clubs.

KW - Back propagation

KW - Modelling or simulation performance drop coefficients

KW - NBA basketball

KW - Offensive and defensive data simulation

UR - http://www.scopus.com/inward/record.url?scp=85123371148&partnerID=8YFLogxK

U2 - 10.7752/jpes.2021.06453

DO - 10.7752/jpes.2021.06453

M3 - Article

AN - SCOPUS:85123371148

SN - 2247-8051

VL - 21

SP - 3339

EP - 3343

JO - Journal of Physical Education and Sport

JF - Journal of Physical Education and Sport

IS - 6

M1 - 453

ER -

Machine learning and the NBA Game

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this