Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball
This work addresses the need for more precise player comparisons and predictions in professional basketball, though it is incremental as it applies existing methods to new data.
The authors tackled the problem of imprecise, heuristic comparisons of NBA players by developing a machine learning approach to analyze shot selection spatial structure, resulting in a low-dimensional representation of offensive player types using non-negative matrix factorization that corresponds to intuitive player descriptions and can model shooting accuracy.
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.