ABSTRACT
Assessing the impact of the individual actions performed by soccer players during games is a crucial aspect of the player recruitment process. Unfortunately, most traditional metrics fall short in addressing this task as they either focus on rare actions like shots and goals alone or fail to account for the context in which the actions occurred. This paper introduces (1) a new language for describing individual player actions on the pitch and (2) a framework for valuing any type of player action based on its impact on the game outcome while accounting for the context in which the action happened. By aggregating soccer players' action values, their total offensive and defensive contributions to their team can be quantified. We show how our approach considers relevant contextual information that traditional player evaluation metrics ignore and present a number of use cases related to scouting and playing style characterization in the 2016/2017 and 2017/2018 seasons in Europe's top competitions.
Supplemental Material
- Daniel Altman. 2015. Beyond Shots: A New Approach to Quantifying Scoring Opportunities. (2015). http://northyardanalytics.com/Dan-Altman-NYA-OptaPro-Forum-2015.pdf OptaPro Analytics Forum.Google Scholar
- Lotte Bransen, Pieter Robberechts, Jan Van Haaren, and Jesse Davis. 2019 a. Choke or Shine? Quantifying Soccer Playersrq Abilities to Perform Under Mental Pressure. In MIT Sloan Sports Analytics Conference.Google Scholar
- Lotte Bransen and Jan Van Haaren. 2018. Measuring Football Playersrq On-the-Ball Contributions from Passes During Games. In ECML/PKDD 2018 Workshop on Machine Learning and Data Mining for Sports Analytics.Google Scholar
- Lotte Bransen, Jan Van Haaren, and Michel van de Velden. 2019 b. Measuring Soccer Playersrq Contributions to Chance Creation by Valuing Their Passes. Journal of Quantitative Analysis in Sports (2019).Google Scholar
- Michael Caley. 2015. Premier League Projections and New Expected Goals . (2015). https://cartilagefreecaptain.sbnation.com/2015/10/19/9295905/premier-league-projections-and-new-expected-goals Cartilage Free Captain.Google Scholar
- Dan Cervone, Alexander D'Amour, Luke Bornn, and Kirk Goldsberry. 2014. POINTWISE: Predicting Points and Valuing Decisions in Real Time with NBA Optical Tracking Data. In MIT Sloan Sports Analytics Conference.Google Scholar
- Tianqi Chen and Carlos Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 785--794. Google ScholarDigital Library
- Tom Decroos, Vladimir Dzyuba, Jan Van Haaren, and Jesse Davis. 2017a. Predicting Soccer Highlights from Spatio-Temporal Match Event Streams. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. 1302--1308. Google ScholarDigital Library
- Tom Decroos, Jan Van Haaren, and Jesse Davis. 2018. Automatic Discovery of Tactics in Spatio-Temporal Soccer Match Data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM. Google ScholarDigital Library
- Tom Decroos, Jan Van Haaren, Vladimir Dzyuba, and Jesse Davis. 2017b. STARSS: A Spatio-temporal Action Rating System for Soccer. In ECML/PKDD 2017 Workshop on Machine Learning and Data Mining for Sports Analytics.Google Scholar
- Javier Fernández, Luke Bornn, and Dan Cervone. 2019. Decomposing the Immeasurable Sport: A Deep Learning Expected Possession Value Framework for Soccer. In MIT Sloan Sports Analytics Conference.Google Scholar
- César Ferri, José Hernández-Orallo, and R. Modroiu. 2009. An Experimental Comparison of Performance Measures for Classification . Pattern Recognition Letters , Vol. 30, 1 (2009), 27--38. Google ScholarDigital Library
- Keith Goldner. 2012. A Markov Model of Football: Using Stochastic Processes to Model a Football Drive . Journal of Quantitative Analysis in Sports , Vol. 8, 1 (2012).Google ScholarCross Ref
- Sam Gregory. 2017. How We Assign Credit in Football . (2017). http://www.optasportspro.com/about/optapro-blog/posts/2017/blog-how-we-assign-credit-in-football/ OptaPro Blog.Google Scholar
- László Gyarmati and Rade Stanojevic. 2016. QPass: A Merit-based Evaluation of Soccer Passes. In KDD 2016 Workshop on Large-Scale Sports Analytics.Google Scholar
- Nobuyoshi Hirotsu, Michael Wright, et almbox. 2002. Using a Markov Process Model of an Association Football Match to Determine the Optimal Timing of Substitution and Tactical Decisions . Journal of the Operational Research Society , Vol. 53, 1 (2002).Google Scholar
- Ted Knutson. 2017. Introducing xGChain. (2017). http://www.statsbombservices.com/introducing-xgchain StatsBomb IQ Services.Google Scholar
- Michael Littman. 1994. Markov Games as a Framework for Multi-Agent Reinforcement Learning. In Proceedings of the International Conference on Machine Learning. Google ScholarDigital Library
- Guiliang Liu and Oliver Schulte. 2018. Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. 3442--3448. Google ScholarDigital Library
- Patrick Lucey, Alina Bialkowski, Mathew Monfort, Peter Carr, and Iain Matthews. 2014. Quality vs. Quantity: Improved Shot Prediction in Soccer Using Strategic Features from Spatiotemporal Data. In MIT Sloan Sports Analytics Conference.Google Scholar
- Nils Mackay. {n.d.}. Predicting Goal Probabilities for Possessions in Football. Master's thesis. Vrije Universiteit Amsterdam.Google Scholar
- Alexandru Niculescu-Mizil and Rich Caruana. 2005. Predicting Good Probabilities with Supervised Learning. In Proceedings of the Twenty-Second International Conference on Machine Learning. 625--632. Google ScholarDigital Library
- Olav Nørstebø , Vegard Rødseth Bjertnes, and Eirik Vabo. 2016. Valuing Individual Player Involvements in Norwegian Association Football. Master's thesis. Norwegian University of Science and Technology.Google Scholar
- Luca Pappalardo, Paolo Cintia, et almbox. 2018. PlayeRank: data-driven performance evaluation and player ranking in soccer via a machine learning approach. arXiv preprint arXiv:1802.04987 (2018).Google Scholar
- Fabian Pedregosa, Gaël Varoquaux, et almbox. 2011. scikit-learn: Machine Learning in Python . Journal of Machine Learning Research , Vol. 12, Oct (2011), 2825--2830. Google ScholarDigital Library
- Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, and Andrey Gulin. 2018. CatBoost: Unbiased Boosting with Categorical Features. In Advances in Neural Information Processing Systems. 6639--6649. Google ScholarDigital Library
- Kurt Routley and Oliver Schulte. 2015. A Markov Game Model for Valuing Player Actions in Ice Hockey. In Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence . 782--791. Google ScholarDigital Library
- Sarah Rudd. 2011. A Framework for Tactical Analysis and Individual Offensive Production Assessment in Soccer Using Markov Chains. In New England Symposium on Statistics in Sports. http://nessis.org/nessis11/rudd.pdfGoogle Scholar
- Tom Tango, Mitchel Lichtman, and Andrew Dolphin. 2007. The Book: Playing the Percentages in Baseball. Potomac Books, Inc.Google Scholar
Recommendations
What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningObjectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for ...
Automatic Discovery of Tactics in Spatio-Temporal Soccer Match Data
KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningSports teams are nowadays collecting huge amounts of data from training sessions and matches. The teams are becoming increasingly interested in exploiting these data to gain a competitive advantage over their competitors. One of the most prevalent types ...
Luck is Hard to Beat: The Difficulty of Sports Prediction
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningPredicting the outcome of sports events is a hard task. We quantify this difficulty with a coefficient that measures the distance between the observed final results of sports leagues and idealized perfectly balanced competitions in terms of skill. This ...
Comments