Action rate models for predicting actions in soccer

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

We present a data-driven approach to predict the next action in soccer. We focus on passing actions of the ball possessing player and aim to forecast the pass itself and when, in time, the pass will be played. At the same time, our model estimates the probability that the player loses possession of the ball before she can perform the action. Our approach consists of parameterized exponential rate models for all possible actions that are adapted to historic data with graph recurrent neural networks to account for inter-dependencies of the output space (i.e., the possible actions). We report on empirical results.

Original languageEnglish
JournalAStA Advances in Statistical Analysis
Volume107
Issue number1-2
Pages (from-to)29-49
Number of pages21
ISSN1863-8171
DOIs
Publication statusPublished - 02.03.2022

Bibliographical note

Publisher Copyright:
© 2022, The Author(s).

Recently viewed

Publications

  1. Factor structure and measurement invariance of the Students’ Self-report Checklist of Social and Learning Behaviour (SSL)
  2. Editorial: Machine Learning and Data Mining in Materials Science
  3. HR practices and ambidexterity in small- and medium-sized consulting firms: An exploratory multi-case study
  4. Reading Comprehension as Embodied Action: Exploratory Findings on Nonlinear Eye Movement Dynamics and Comprehension of Scientific Texts
  5. The representative turn in EU studies
  6. Late developers and the inequity of "equitable utilization" and the harm of "do no harm"
  7. Machine Learning and Knowledge Discovery in Databases
  8. What factors enable social-ecological transformative potential? The role of learning practices, empowerment, and networking
  9. Comparison of Backpropagation and Kalman Filter-based Training for Neural Networks
  10. Integration durch soziale Kontrolle?
  11. An Equation with many Variables
  12. Head turn scaling below the threshold of perception in immersive virtual environments
  13. What can we learn from bargaining models about union power?
  14. Optimization of a gaseous multitube detector for soft X-ray detection
  15. Introduction to ‘Exploring the frontiers: unveiling new horizons in carbon efficient biomass utilization’
  16. Mining positional data streams
  17. Alternating between Partial and Complete Organization
  18. Introduction to the challenges and chances regarding the utilization of nitrogen-rich by-products and waste streams
  19. Anatomy of Discrete Kalman Filter and Its Implementation for Sensorless Velocity Estimation of Organic Actuator
  20. Are criminals better lie detectors? Investigating offenders' abilities in the context of deception detection
  21. An EKF-based observer for sensorless valve control in camless internal combustion engine
  22. Spatially assessing unpleasant places with hard- and soft-GIS methods