Evaluation of Creating Scoring Opportunities for Teammates in Soccer via Trajectory Prediction

Teranishi, Masaki; Tsutsui, Kazushi; Takeda, Kazuya; Fujii, Keisuke

doi:10.1007/978-3-031-27527-2_5

Cited by 14 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in more general cases, all agents (in basketball, 11 agents) should be considered. A graph neural network [49], [51], [61] could be applied to improve predictability and a Gaussian mixture model [47], [50] to address the role assignment problem in order to improve the interpretability of this problem. Combining improvements in predictability and interpretability remains an avenue for future work.…”

Section: Discussionmentioning

confidence: 99%

Multi-Agent Deep-Learning Based Comparative Analysis of Team Sport Trajectories

et al. 2023

View full text Add to dashboard Cite

Computational analysis of multi-agent trajectories is a fundamental issue in the study of real-world biological agents. For trajectory analysis, combining movement data with labels (e.g., whether a team scores in a ball game) can provide additional insights compared to relying only on trajectory data. However, existing deep-learning-based methods consider only single-agent animal trajectories, and cannot be directly applied to multi-agent trajectories in sports. In this paper, a comparative analysis method to analyze multi-agent trajectories in ball games is proposed. A neural network approach using multi-agent motion characteristics (e.g., the distances between agents and objects) as the input is adopted, which is based on an attention mechanism designed to automatically detect segments in trajectories that are characteristic of a given class. This enables us to understand differences between classes by highlighting segmented trajectories and which variables correlate with the given labels. The effectiveness of our approach was verified by comparing various baselines with effective/ineffective attack labels and goal/non-goal labels using different sizes of the dataset. The effectiveness of our method is also demonstrated through a use case that analyzes the attacking plays in an NBA dataset.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Agent Deep-Learning Based Comparative Analysis of Team Sport Trajectories

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Since then, there have been multiple metrics proposed to resolve the limitation. For instance, the probability an off-ball player will score in the next action known as an offball scoring opportunity (OBSO) [26] (the variant is [27]), the probability that a pass is converted into an assist known as an expected assist (xA) https: //www.statsperform.com/opta-analytics/, and score opportunities a player can create via passing or shooting known as an expected threat (xT) https: //karun.in/blog/expected-threat.html.…”

Section: Related Workmentioning

confidence: 99%

Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis

Yeung¹,

Sit²,

Fujii³

2023

Preprint

View full text Add to dashboard Cite

With recently available football match event data that record the details of football matches, analysts and researchers have a great opportunity to develop new performance metrics, gain insight, and evaluate key performance. However, most sports sequential events modeling methods and performance metrics approaches could be incomprehensive in dealing with such large-scale spatiotemporal data (in particular, temporal process), thereby necessitating a more comprehensive spatiotemporal model and a holistic performance metric. To this end, we proposed the Transformer-Based Neural Marked Spatio Temporal Point Process (NM-STPP) model for football event data based on the neural temporal point processes (NTPP) framework. In the experiments, our model outperformed the prediction performance of the baseline models. Furthermore, we proposed the holistic possession utilization score (HPUS) metric for a more comprehensive football possession analysis. For verification, we examined the relationship with football teams' final ranking, average goal score, and average xG over a season. It was observed that the average HPUS showed significant correlations regardless of not using goal and details of shot information. Furthermore, we show HPUS examples in analyzing possessions, matches, and between matches.

show abstract

“…We performed zero-padding if the length of the possessions was less than 𝑇 and did not perform back-propagation about the zero-padding frames. The tracking data were down-sampled to 10 Hz based on [11], [31]. We analyzed 10 attacking players (without a goalkeeper), i.e., constructed 10 RL agent models.…”

Section: Dataset and Preprocessingmentioning

confidence: 99%

“…Another study [11] quantified every off-ball player's impact on scores in terms of the difference between predicted and real player movements. The method quantitatively values only a single player's contribution once through their predicted movement trajectories.…”

Section: Introductionmentioning

confidence: 99%

Action Valuation of On- and Off-Ball Soccer Players Based on Multi-Agent Deep Reinforcement Learning

Nakahara,

Tsutsui,

Takeda

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous studies using deep reinforcement learning have often considered teams as a single agent and valued the teams and players who hold the ball in each discrete event. Then it was challenging to value the actions of multiple players, including players far from the ball, in a spatiotemporally continuous state space. In this paper, we propose a method of valuing possible actions for on-and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning. We consider a discrete action space in each data frame that mimics that of Google research football and leverages supervised learning for actions in reinforcement learning. In the experiment, we analyzed the relationships with conventional indicators, season goals, and game ratings by experts, and showed the effectiveness of the proposed method. Our approach can assess how multiple players move continuously throughout the game, which is difficult to be discretized or labeled but vital for teamwork, scouting, and fan engagement.

show abstract

Evaluation of Creating Scoring Opportunities for Teammates in Soccer via Trajectory Prediction

Cited by 14 publications

References 27 publications

Multi-Agent Deep-Learning Based Comparative Analysis of Team Sport Trajectories

Multi-Agent Deep-Learning Based Comparative Analysis of Team Sport Trajectories

Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis

Action Valuation of On- and Off-Ball Soccer Players Based on Multi-Agent Deep Reinforcement Learning

Contact Info

Product

Resources

About