Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction

@article{Yue2014LearningFS,
  title={Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction},
  author={Yisong Yue and Patrick Lucey and Peter Carr and Alina Bialkowski and Iain Matthews},
  journal={2014 IEEE International Conference on Data Mining},
  year={2014},
  pages={670-679}
}
We consider the problem of learning predictive models for in-game sports play prediction. [] Key Method We employ a latent factor modeling approach, which leads to a compact data representation that enables efficient prediction given raw spatiotemporal tracking data. We validate our approach using tracking data from the 2012-2013 NBA season, and show that our model can make accurate in-game predictions. We provide a detailed inspection of our learned factors, and show that our model is interpretable and…
Diverse Generation for Multi-Agent Sports Games
TLDR
A new generative model for multi-agent trajectory data, focusing on the case of multi-player sports games, that leverages graph neural networks and variational recurrent neural networks to achieve a permutation equivariant model suitable for sports.
DeepHoops: Evaluating Micro-Actions in Basketball Using Deep Feature Representations of Spatio-Temporal Data
TLDR
A deep learning framework DeepHoops is developed to process a unique dataset composed of spatio-temporal tracking data from NBA games in order to generate a running stream of predictions on the expected points to be scored as a possession progresses, and is demonstrated to be well-calibrated.
PROGRAMMATIC WEAK SUPERVISION
TLDR
This work presents a hierarchical framework that can effectively learn sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay, and is inspired by recent work on leveraging programmatically produced weak labels, which it extends to the spatiotemporal regime.
Learning Long-term Planning in Basketball Using Hierarchical Memory Networks
TLDR
This work proposes to learn a hierarchical planner that reasons about both longterm and short-term goals, which is instantiate as a hierarchical deep memory network and generates significantly more realistic trajectories compared to non-hierarchical baselines as judged by professional sports analysts.
Rugby-Bot: Utilizing Multi-Task Learning & Fine-Grained Features for Rugby League Analysis
TLDR
This work presents a multi-task learning method of generating multiple predictions for analysis via a single prediction source using a fine- grain representation using fine-grain spatial data using a wide-and-deep learning approach.
Predicting Sports Scoring Dynamics with Restoration and Anti-Persistence
TLDR
Novel interpretable generative models of within-game scoring that allow for dependence on lead size and on the last team to score are presented and applied to comprehensive within- game scoring data for four sports leagues over a ten-year period.
"Quality vs Quantity": Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data
In this paper, we present a method which accurately estimates the likelihood of chances in soccer using strategic features from an entire season of player and ball tracking data taken from a
Generating Multi-Agent Trajectories using Programmatic Weak Supervision
TLDR
This work presents a hierarchical framework that can effectively learn sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay, and is inspired by recent work on leveraging programmatically produced weak labels, which it extends to the spatiotemporal regime.
Predicting the outcome of team movements - Player time series analysis using fuzzy and deep methods for representation learning
TLDR
A framework for the useful encoding of short tactics and space occupations in a more extended sequence of movements or tactical plans is provided for the professional basketball SportVU dataset for the 2015-16 half-season.
A Statistical Model of Serve Return Impact Patterns in Professional Tennis
TLDR
This model was motivated by the efforts to describe common styles of return impact location of professional tennis players and is the reason it is named a ‘latent style allocation’ model.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball
TLDR
A machine learning approach to represent and analyze the underlying spatial structure that governs shot selection among professional basketball players in the NBA shows that a low-rank spatial decomposition summarizes the shooting habits of NBA players.
Large-Scale Analysis of Formations in Soccer
TLDR
This work finds the most likely formation patterns of a team associated with match events across nearly 14 hours of continuous player and ball tracking data in soccer and shows that it can accurately segment a match into distinct game phases and detect highlights.
POINTWISE: Predicting Points and Valuing Decisions in Real Time with NBA Optical Tracking Data
TLDR
A modeling framework for estimating expected possession value (EPV), which allows analysts to evaluate every decision made during a basketball game – whether it is to pass, dribble, or shoot – opening the door for a multitude of new metrics and analyses of basketball that quantify value in terms of points.
Acceleration in the NBA: Towards an Algorithmic Taxonomy of Basketball Plays
I filter the 25-frames-per-second STATS/SportVu optical tracking data of 233 regular and post season 2011-2012 NBA games for half-court situations that begin when the last player crosses half-court
You'll never walk alone: Modeling social behavior for multi-target tracking
TLDR
A model of dynamic social behavior, inspired by models developed for crowd simulation, is introduced, trained with videos recorded from birds-eye view at busy locations, and applied as a motion model for multi-people tracking from a vehicle-mounted camera.
Characterizing the spatial structure of defensive skill in professional basketball
Although basketball is a dualistic sport, with all players competing on both offense and defense, almost all of the sport's conventional metrics are designed to summarize offensive play. As a result,
Win at Home and Draw Away ” : Automatic Formation Analysis Highlighting the Differences in Home and Away Team Behaviors
TLDR
It is shown that while teams tend to play the same formation at home as they do away, the manner in which they execute the formation is significantly different and this conservative approach at away games suggests that coaches aim to win their home games and draw their away games.
Incorporating side information into probabilistic matrix factorization using Gaussian Processes
TLDR
This work proposes a framework for incorporating side information in Probabilistic matrix factorization by coupling together multiple PMF problems via Gaussian process priors, and replaces scalar latent features with functions that vary over the covariate space.
Basketball Teams as Strategic Networks
TLDR
The analyses demonstrate the utility of network approaches in quantifying team strategy and show that testable hypotheses can be evaluated using this approach, and highlight the richness of basketball networks as a dataset for exploring the relationships between network structure and dynamics with team organization and effectiveness.
Computational Rationalization: The Inverse Equilibrium Problem
TLDR
Employing the game-theoretic notion of regret and the principle of maximum entropy, this work introduces a technique for predicting and generalizing behavior in competitive and cooperative multi-agent domains.
...
1
2
3
4
...