A Multiresolution Stochastic Process Model for Predicting Basketball Possession Outcomes
TL;DR: A framework for using optical player tracking data to estimate, in real time, the expected number of points obtained by the end of a possession, called expected possession value (EPV), derives from a stochastic process model for the evolution of a basketball possession.
read more
Abstract: Basketball games evolve continuously in space and time as players constantly interact with their teammates, the opposing team, and the ball. However, current analyses of basketball outcomes rely on discretized summaries of the game that reduce such interactions to tallies of points, assists, and similar events. In this paper, we propose a framework for using optical player tracking data to estimate, in real time, the expected number of points obtained by the end of a possession. This quantity, called \textit{expected possession value} (EPV), derives from a stochastic process model for the evolution of a basketball possession; we model this process at multiple levels of resolution, differentiating between continuous, infinitesimal movements of players, and discrete events such as shot attempts and turnovers. Transition kernels are estimated using hierarchical spatiotemporal models that share information across players while remaining computationally tractable on very large data sets. In addition to estimating EPV, these models reveal novel insights on players' decision-making tendencies as a function of their spatial strategy.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Spatio-Temporal Analysis of Team Sports -- A Survey
TL;DR: This article categorises the research efforts that use spatio-temporal data from team sports as input and involve non-trivial computation in a coherent framework and identifies a number of open research questions.
Sports analytics — Evaluation of basketball players and team performance
TL;DR: Background and advanced basketball metrics used in National Basketball Association (NBA) and Euroleague games are reviewed to benchmark existing performance analytics used in the literature for evaluating teams and players.
134
Real Time Quantification of Dangerousity in Football Using Spatiotemporal Tracking Data.
TL;DR: These metrics provide a criterion that does not depend on chance or results to investigate the influence of central events in a match, various playing systems or tactical group concepts on success, and to characterise the performance and efficiency of teams over the season.
Not All Passes Are Created Equal: Objectively Measuring the Risk and Reward of Passes in Soccer from Tracking Data
Paul Power,Hector Ruiz,Xinyu Wei,Patrick Lucey +3 more
- 13 Aug 2017
TL;DR: This paper shows how to estimate both the risk and reward of a pass across two seasons of tracking data captured from a recent professional soccer league with state-of-the-art performance, then showcases various use cases of the deployed passing system.
121
Deep soccer analytics: learning an action-value function for evaluating soccer players
TL;DR: A novel soccer Goal Impact Metric (GIM) applies values from the learned Q-function, to measure a player’s overall performance by the aggregate impact values of his actions over all the games in a season, and its correlations with standard measures of soccer success are higher than that computed with other state-of-the-art soccer metrics.
99
References
Gaussian processes in machine learning
TL;DR: In this paper, the authors give a basic introduction to Gaussian Process regression models and present the simple equations for incorporating training data and examine how to learn the hyperparameters using the marginal likelihood.
Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations
TL;DR: This work considers approximate Bayesian inference in a popular subset of structured additive regression models, latent Gaussian models, where the latent field is Gaussian, controlled by a few hyperparameters and with non‐Gaussian response variables and can directly compute very accurate approximations to the posterior marginals.
•Journal Article
Rejoinder (Bayesian image restoration,with two applications in spatial statistics)
TL;DR: The present paper argues that many problems in the analysis of spatial data can be interpreted as problems of image restoration, since the amounts of data involved allow routine use of computer intensive methods, such as the Gibbs sampler, that are not yet practicable for conventional images.
3.5K
An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
TL;DR: It is shown that, using an approximate stochastic weak solution to (linear) stochastically partial differential equations, some Gaussian fields in the Matérn class can provide an explicit link, for any triangulation of , between GFs and GMRFs, formulated as a basis function representation.
2.9K