Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball

Andrew Miller, Luke Bornn, Ryan Adams, Kirk Goldsberry
; Proceedings of the 31st International Conference on Machine Learning, PMLR 32(1):235-243, 2014.

Abstract

We develop a machine learning approach to represent and analyze the underlying spatial structure that governs shot selection among professional basketball players in the NBA. Typically, NBA players are discussed and compared in an heuristic, imprecise manner that relies on unmeasured intuitions about player behavior. This makes it difficult to draw comparisons between players and make accurate player specific predictions. Modeling shot attempt data as a point process, we create a low dimensional representation of offensive player types in the NBA. Using non-negative matrix factorization (NMF), an unsupervised dimensionality reduction technique, we show that a low-rank spatial decomposition summarizes the shooting habits of NBA players. The spatial representations discovered by the algorithm correspond to intuitive descriptions of NBA player types, and can be used to model other spatial effects, such as shooting accuracy.

Cite this Paper


BibTeX
@InProceedings{pmlr-v32-miller14, title = {Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball}, author = {Andrew Miller and Luke Bornn and Ryan Adams and Kirk Goldsberry}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {235--243}, year = {2014}, editor = {Eric P. Xing and Tony Jebara}, volume = {32}, number = {1}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/miller14.pdf}, url = {http://proceedings.mlr.press/v32/miller14.html}, abstract = {We develop a machine learning approach to represent and analyze the underlying spatial structure that governs shot selection among professional basketball players in the NBA. Typically, NBA players are discussed and compared in an heuristic, imprecise manner that relies on unmeasured intuitions about player behavior. This makes it difficult to draw comparisons between players and make accurate player specific predictions. Modeling shot attempt data as a point process, we create a low dimensional representation of offensive player types in the NBA. Using non-negative matrix factorization (NMF), an unsupervised dimensionality reduction technique, we show that a low-rank spatial decomposition summarizes the shooting habits of NBA players. The spatial representations discovered by the algorithm correspond to intuitive descriptions of NBA player types, and can be used to model other spatial effects, such as shooting accuracy.} }
Endnote
%0 Conference Paper %T Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball %A Andrew Miller %A Luke Bornn %A Ryan Adams %A Kirk Goldsberry %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-miller14 %I PMLR %J Proceedings of Machine Learning Research %P 235--243 %U http://proceedings.mlr.press %V 32 %N 1 %W PMLR %X We develop a machine learning approach to represent and analyze the underlying spatial structure that governs shot selection among professional basketball players in the NBA. Typically, NBA players are discussed and compared in an heuristic, imprecise manner that relies on unmeasured intuitions about player behavior. This makes it difficult to draw comparisons between players and make accurate player specific predictions. Modeling shot attempt data as a point process, we create a low dimensional representation of offensive player types in the NBA. Using non-negative matrix factorization (NMF), an unsupervised dimensionality reduction technique, we show that a low-rank spatial decomposition summarizes the shooting habits of NBA players. The spatial representations discovered by the algorithm correspond to intuitive descriptions of NBA player types, and can be used to model other spatial effects, such as shooting accuracy.
RIS
TY - CPAPER TI - Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball AU - Andrew Miller AU - Luke Bornn AU - Ryan Adams AU - Kirk Goldsberry BT - Proceedings of the 31st International Conference on Machine Learning PY - 2014/01/27 DA - 2014/01/27 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-miller14 PB - PMLR SP - 235 DP - PMLR EP - 243 L1 - http://proceedings.mlr.press/v32/miller14.pdf UR - http://proceedings.mlr.press/v32/miller14.html AB - We develop a machine learning approach to represent and analyze the underlying spatial structure that governs shot selection among professional basketball players in the NBA. Typically, NBA players are discussed and compared in an heuristic, imprecise manner that relies on unmeasured intuitions about player behavior. This makes it difficult to draw comparisons between players and make accurate player specific predictions. Modeling shot attempt data as a point process, we create a low dimensional representation of offensive player types in the NBA. Using non-negative matrix factorization (NMF), an unsupervised dimensionality reduction technique, we show that a low-rank spatial decomposition summarizes the shooting habits of NBA players. The spatial representations discovered by the algorithm correspond to intuitive descriptions of NBA player types, and can be used to model other spatial effects, such as shooting accuracy. ER -
APA
Miller, A., Bornn, L., Adams, R. & Goldsberry, K.. (2014). Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball. Proceedings of the 31st International Conference on Machine Learning, in PMLR 32(1):235-243

Related Material