Soccer Analytics 2023 Review

Collection of the soccer analytics content that I liked the most in 2023!

This year at the StatsBomb Conference I learned that my review blog posts no longer need introducing. I was pleasantly surprised to hear from multiple participants in the conference’s research-paper competition that my annual blog posts had helped them enter this exciting field and shape their research ideas. When I started this series of blog posts, I had precisely that goal in mind. Needless to say, I hope this overview of the soccer analytics content that I liked the most in 2023 will inspire another generation of soccer analytics enthusiasts in the new year!

This blog post provides pointers to research papers, blog posts, news articles, podcasts, events and code repositories that are related to soccer analytics. The selection focuses on resources that provide new insights in the field of soccer analytics, address interesting challenges, propose new methods for analyzing the game, or apply existing methods in a creative or novel way.

If you are new to the field, you might want to skim through my review blog posts from 2022, 2021 and 2020. You might also want to check out the Resources page that provides pointers to open datasets, Python libraries, book recommendations and career advice blog posts among others.

Research papers (58)

• What Should Clubs Monitor to Predict Future Value of Football Players. Ali Baouan, Elsa Bismuth, Aurèle Bohbot, Sébastien Coustou, Mathieu Lacome and Mathieu Rosenbaum. arXiv pre-print. December 2022.
• Determinants of Football Players’ Valuation: A Systematic Review. Maxence Franceschi, Jean-François Brocard, Florian Follert and Jean-Jacques Gouguet. Journal of Economic Surveys. February 2023.
• Towards Maximizing Expected Possession Outcome in Soccer. Pegah Rahimian, Jan Van Haaren and Laszlo Toka. International Journal of Sports Science & Coaching. February 2023.
• A Data-driven Approach to Assist Offensive and Defensive Players in Optimal Decision Making. Pegah Rahimian and Laszlo Toka. International Journal of Sports Science & Coaching. February 2023.
• Fairer Shootouts in Soccer: The m−n Rule. Steven Brams, Mehmet Ismail and Marc Kilgour. arXiv pre-print. February 2023.
• Why Winning a Soccer Game Is Worth 5 Points. Leszek Szczecinski. arXiv pre-print. February 2023.
• Beating the Average: How to Generate Profit by Exploiting the Inefficiencies of Soccer Betting. Ralph Stömmer. arXiv pre-print. March 2023.
• Tactical Behaviour in Professional Soccer. Floris Goes. PhD Thesis. March 2023.
• Soccer Analytics. Lucas Wu. PhD Thesis. March 2023.
• Player Tracking Data in Sports. Stephanie Kovalchik. Annual Review of Statistics and Its Application. March 2023.
• A Data-Driven Framing of Player and Team Performance in U.S. Women’s Soccer. Sachin Narayanan and David Pifer. Frontiers in Sports and Active Living. March 2023.
• Putting Team Formations in Association Football Into Context. Pascal Bauer, Gabriel Anzer and Laurie Shaw. Journal of Sports Analytics. March 2023.
• A Graph Neural Network Deep-Dive Into Successful Counterattacks. Amod Sahasrabudhe and Joris Bekkers. MIT Sloan Sports Analytics Conference. March 2023. Code. Video.
• Towards Active Learning for Action Spotting in Association Football Videos. Silvio Giancola, Anthony Cioppa, Julia Georgieva, Johsan Billingham, Andreas Serner, Kerry Peek, Bernard Ghanem and Marc Van Droogenbroeck. CVPR 2023 International Workshop on Computer Vision in Sports. April 2023.
• VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views. Jan Held, Anthony Cioppa, Silvio Giancola, Abdullah Hamdi, Bernard Ghanem and Marc Van Droogenbroeck. CVPR 2023 International Workshop on Computer Vision in Sports. April 2023.
• Optimal Selection of the Starting Lineup for a Football Team. Soudeep Deb and Shubhabrata Das. arXiv pre-print. April 2023.
• Crediting Football Players for Creating Dangerous Actions in an Unbiased Way: The Generation of Threat (GoT) Indices. Ali Baouan, Sébastien Coustou, Mathieu Lacome, Sergio Pulido and Mathieu Rosenbaum. arXiv pre-print. April 2023.
• Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations. Gregory Everett, Ryan Beal, Tim Matthews, Joseph Early, Timothy Norman and Sarvapali Ramchurn. Proceedings of the International Conference on Autonomous Agents and Multiagent Systems. May 2023.
• Presenting Multiagent Challenges in Team Sports Analytics. David Radke and Alexi Orchard. Proceedings of the International Conference on Autonomous Agents and Multiagent Systems. May 2023.
• Is a Compact Organization Important for Defensive Success in Elite Soccer? Analysis Based on Player Tracking Data. Leander Forcher, Leon Forcher, Stefan Altmann, Darko Jekauc and Matthias Kempe. International Journal of Sports Science & Coaching. May 2023.
• A Markov Framework for Learning and Reasoning About Strategies in Professional Soccer. Maaike Van Roy, Pieter Robberechts, Wen-Chi Yang, Luc De Raedt, Jesse Davis. Journal of Artificial Intelligence Research. June 2023.
• But Could They Do It On A Cold, Rainy Night in Stoke? Measuring Player Performance Through Predicted Team Behaviour. Olly Craven. Bachelor Thesis. June 2023.
• Correction of Systematic Errors in Electronic Performance and Tracking Systems. Marc Schmid and Martin Lames. Sports Engineering. June 2023.
• Stop Simulating! Efficient Computation of Tournament Winning Probabilities. Ulrik Brandes. arXiv pre-print. July 2023.
• A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory. Calvin Yeung and Keisuke Fujii. arXiv pre-print. July 2023.
• Extending the Dixon and Coles Model: An Application to Women’s Football Data. Rouven Michels, Marius Ötting and Dimitris Karlis. arXiv pre-print. July 2023.
• Prediction of Defensive Success in Elite Soccer Using Machine Learning - Tactical Analysis of Defensive Play Using Tracking Data and Explainable AI. Leander Forcher, Tobias Beckmann, Oliver Wohak, Christian Romeike, Ferdinand Graf and Stefan Altmann. Science and Medicine in Football. August 2023.
• Un-XPass: Measuring Soccer Player’s Creativity. Pieter Robberechts, Maaike Van Roy and Jesse Davis. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining. August 2023. Code.
• Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set Transformer and Hierarchical Bi-LSTM. Hyunsung Kim, Han-Jun Choi, Chang Jo Kim, Jinsung Yoon and Sang-Ki Ko. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining. August 2023.
• Miss It Like Messi: Extracting Value from Off-Target Shots in Soccer. Ethan Baron, Nathan Sandholtz, Devin Pleuler and Timothy Chan. arXiv pre-print. August 2023.
• A Machine Learning Approach for Player and Position Adjusted Expected Goals in Football (Soccer). James Hewitt and Oktay Karakuş. Franklin Open. August 2023.
• Expected Metrics as a Measure of Skill: Reflections on Finishing in Soccer. Jesse Davis and Pieter Robberechts. ECML/PKDD 2023 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2023). September 2023.
• Pass Receiver and Outcome Prediction in Soccer Using Temporal Graph Networks. Pegah Rahimian, Hyunsung Kim, Marc Schmid and Laszlo Toka. ECML/PKDD 2023 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2023). September 2023.
• Evaluating Soccer Match Prediction Models: A Deep Learning Approach and Feature Optimization for Gradient-Boosted Trees. Calvin Yeung, Rory Bunker, Rikuhei Umemoto and Keisuke Fujii. arXiv pre-print. September 2023.
• StratAlign: Uncovering Tactical Patterns Through Large-Scale Event Sequence Matching. Ahmed El-Roby, Abdelrahman Hefny and Alireza Choubineh. StatsBomb Conference. October 2023. Video.
• An Events and 360 Data-Driven Approach for Extracting Team Tactics and Evaluating Performance in Football. Calvin Yeung and Rory Bunker. StatsBomb Conference. October 2023.
• An Analysis of the Influence of Game Context on Team Playing Style. Deniz Can Oruç, Lorenzo Cascioli, Luca Stradiotti, Maaike Van Roy, Pieter Robberechts and Jesse Davis. StatsBomb Conference. October 2023. Video.
• Clustering Women’s Football Players - Identifying Functional Patterns for Performance Optimisation. Maia Trower, Niamh Graham, Natasha Cottrell and Yasmin Hengster. StatsBomb Conference. October 2023. Video.
• Leveraging Team Traces to Optimise Process-Aware Tactical Style Discovery. Marc Garnica Caparrós. StatsBomb Conference. October 2023. Video.
• TacticalGPT - Uncovering the Potential of LLMs for Predicting Tactical Decisions in Professional Football. Matthew Caron and Oliver Müller. StatsBomb Conference. October 2023.
• Identifying Key Players & Playing Styles of 10 English Premier League Teams During Offensive Sequences in 2021-2022 Season. Praful Upadhyay and Janik Backhaus. StatsBomb Conference. October 2023. Video.
• Measuring Player Performance Through Predicting Team Actions. Olly Craven. StatsBomb Conference. October 2023. Video.
• Evaluation of Team Defense Positioning by Computing Counterfactuals Using StatsBomb 360 Data. Rikuhei Umemoto and Keisuke Fujii. StatsBomb Conference. October 2023. Video.
• Clustering Football Game Situations via Deep Representation Learning. Zitian Tang, Xing Wang and Shaoliang Zhang. StatsBomb Conference. October 2023. Video.
• In Professional Football the Decline in High-Intensity Running Activities from First to Second Half Is More Pronounced in Players with a Fast Muscle Typology. Freek Van de Casteele, Dieter Deprez, Jan Van Haaren, Wim Derave and Eline Lievens. Scandinavian Journal of Medicine & Science in Sports. October 2023.
• TacticAI: An AI Assistant for Football Tactics. Zhe Wang, Petar Veličković, Daniel Hennes, Nenad Tomašev, Laurel Prince, Michael Kaisers, Yoram Bachrach, Romuald Elie, Li Kevin Wenliang, Federico Piccinini, William Spearman, Ian Graham, Jerome Connor, Yi Yang, Adrià Recasens, Mina Khan, Nathalie Beauguerlange, Pablo Sprechmann, Pol Moreno, Nicolas Heess, Michael Bowling, Demis Hassabis and Karl Tuyls. arXiv pre-print. October 2023.
• Ratings of European and South American Football Leagues Based on Glicko-2 With Modifications. Andrei Shelopugin and Alexander Sirotkin. arXiv pre-print. October 2023. Code.
• Penalty Shootouts Are Tough, but the Alternating Order Is Fair. Silvan Vollmer, David Schoch and Ulrik Brandes. arXiv pre-print. October 2023.
• Passing Heatmap Prediction Based on Transformer Model and Tracking Data. Yisheng Pei, Varuna De Silva and Mike Caine. arXiv pre-print. October 2023.
• A Goal-Aligned Coordinate System for Invasion Games. Ulrik Brandes. Journal of Sports Analytics. November 2023.
• Action Valuation of On- and Off-Ball Soccer Players Based on Multi-Agent Deep Reinforcement Learning. Hiroshi Nakahara, Kazushi Tsutsui, Kazuya Takeda and Keisuke Fujii. IEEE Access. November 2023.
• Club Coefficients in the UEFA Champions League: Time for Shift to an Elo-Based Formula. László Csató. International Journal of Performance Analysis in Sport. November 2023.
• Continuous Football Player Tracking From Discrete Broadcast Data. Matthew Penn, Christl Donnelly and Samir Bhatt. arXiv pre-print. November 2023. Code.
• Setting a Baseline for Long-shot Real-time Player and Ball Detection in Soccer Videos. Konstantinos Moutselos and Ilias Maglogiannis. arXiv pre-print. November 2023. Code.
• Explainable Artificial Intelligence Model for Identifying Market Value in Professional Soccer Players. Chunyang Huang and Shaoliang Zhang. arXiv pre-print. November 2023.
• The Success Factors of Rest Defense in Soccer – A Mixed-Methods Approach of Expert Interviews, Tracking Data, and Machine Learning. Leander Forcher, Leon Forcher, Stefan Altmann, Darko Jekauc and Matthias Kempe. Journal of Sports Science and Medicine. December 2023.
• A Multilayer Network Framework for Soccer Analysis. Álvaro Novillo, Bingnan Gong, Johann Martínez, Ricardo Resta, Roberto López del Campo and Javier Buldú. Chaos, Solitons & Fractals. December 2023.
• Challenges and Considerations in Determining the Quality of Electronic Performance & Tracking Systems for Team Sports. Sam Robertson, Grant Malcolm Duthie, Kevin Ball, Bartholomew Spencer, Fabio Rubens Serpiello, Jade Haycraft, Nicolas Evans, Johsan Billingham and Robert James Aughey. Frontiers in Sports and Active Living. December 2023.

Blog posts (49)

• Introducing Gegenpressing Intensity (GPI). Soccerment. Soccerment. December 2022.
• Does AI Have a Role in the Future of Sport?. Sam Robertson. Victoria University. January 2023.
• Every Question You Need to Ask About Running Stats. Mark Thompson. Get Goalside. January 2023.
• What Continues to Pique My Interest Regarding Football, Numbers and Front Office Theory. Tiotal Football. Absolute Unit. February 2023.
• A Defensive Stats Personal Library. Mark Thompson. Get Goalside. January 2023.
• An Advanced Defensive Data Personal Library. Mark Thompson. Get Goalside. February 2023.
• xG Model Calibration. Tony ElHabr. Personal blog. February 2023.
• Brighton and Brentford: Two Smart Clubs Who Play the Game in Opposite Ways. Brian McDonnell. The Analyst. March 2023.
• Goalkeeper Passing: Risk Versus Reward. Alex Stewart and MarkStats. Analytics FC. March 2023.
• Expected Shots. Sezer Unar. Personal blog. March 2023.
• One-Twos: A New Metric for Associative Ball Progression and Chance Creation. Soccerment. Soccerment. March 2023.
• Rendering Football Data in 3D with Rust and Bevy. Joris Bekkers. Unravel Sports. April 2023.
• Constructing Metrics. Mark Connor. Data Science for Sport. April 2023.
• Box Scores: Analysing Bodies in the Box Data. Oliver Walker. StatsBomb. April 2023.
• Building an AI-Powered Football Commentator. Michael Fordham. Better Programming. April 2023.
• A Pandora’s Box of Football Media Stats Use. Mark Thompson. Get Goalside. April 2023.
• Is Football Media Making the Most of Football Data?. Casey Evans. Analytics FC. April 2023.
• Goals Subtracted (g-): Set Piece Edition. Matthias Kullowatz. American Soccer Analysis. April 2023.
• Ranking Players: Percentile Ranks, Z-Scores and Similarities. Marc Lamberts. Personal blog. May 2023.
• Measuring Pass Success Probability in Football using Tree-Based Models. Alex Marin Felices. Personal blog. May 2023.
• Introducing HOPS: A New Way to Evaluate Heading Ability. StatsBomb. StatsBomb. May 2023.
• 2023 MLS Analytics Survey. Eliot McKinley. American Soccer Analysis. May 2023.
• Stats of MLS Analytics: May 2023. Eliot McKinley. American Soccer Analysis. May 2023.
• The Cost of Injuries in the Premier League. Jason McKenna. Analytics FC. June 2023.
• Unraveling the Strategy of Soccer Substitutions Using Data. Joan Hernanz i Ibáñez, Maaike Van Roy and Jesse Davis. DTAI Sports Analytics Lab. June 2023.
• Careful Clustering of Soccer Players. Ron Yurko. Open Source Sports. July 2023.
• The Genesis of Goalkeeper Chains. Neel Shelat. Analytics FC. July 2023.
• Thomas Bayes? Meet Djordje Petrovic. Mike Imburgio and Kieran Doyle. American Soccer Analysis. August 2023.
• Building a Soccer Player Recommendation System. Sameer Koppolu. Personal blog. August 2023.
• Do Goalkeeper Statistics Reflect Individual Ability or Team Performance?. Eduin Latimer. Analytics FC. August 2023.
• Using Advanced Data to Inform Set Piece Strategy. Scott Johnson. StatsBomb. August 2023.
• The Replication Project: Measuring Shooting Overperformance. Tony ElHabr. American Soccer Analysis. August 2023.
• Measuring Shooting Overperformance in Soccer. Tony ElHabr. Personal blog. August 2023.
• Time to Give Ball-In-Play Measures a Kick Into Touch?. Mark Thompson. Get Goalside. August 2023.
• About Contextualized Plus-Minus (CPM). Invisible Goals. Google Docs. August 2023.
• How to Become a Football Analyst in 2023. Liam Henshaw. Personal blog. August 2023.
• Scrape & Analyze Football Data with Kestra, Malloy and DuckDB. Benoit Pimpaud. Personal blog. September 2023.
• Net Goals Added: Combining Complementary Possession Value Metrics. Mike Imburgio. American Soccer Analysis. September 2023.
• Goalkeeper Chains: How and Why. Neel Shelat. Analytics FC. September 2023.
• Calibrating Binary Probabilities. Tony ElHabr. Personal blog. September 2023.
• StatsBomb Release New Models: Expected Pass (xPass) and Pass Clustering. StatsBomb. StatsBomb. October 2023.
• Purpose of Innovation; Process of Innovation. Mark Thompson. Get Goalside. October 2023.
• What Can We Learn About the Goalkeeping Market From Data?. Alex Stewart. Analytics FC. October 2023.
• So… Everyone’s a Decision-Maker Now. Mark Thompson. Get Goalside. October 2023.
• 2023 StatsBomb Conference: Research Posters. StatsBomb. StatsBomb. November 2023.
• Offense / Defense Framework. Tiotal Football. Absolute Unit. November 2023.
• Quantifying Second-Ball Wins. Chun Hang. Personal blog. November 2023.
• Identifying Fast Passers Using Data. Jaymes Monte. StatsBomb. December 2023.
• ETSY: A Rule-Based Approach to Event and Tracking Data Synchronization. Maaike Van Roy, Lorenzo Cascioli and Jesse Davis. DTAI Sports Analytics Lab. December 2023.

News articles (25)

• Does Scouting in Football Work?. John Muller. The Athletic. January 2023.
• How Ajax Are Building a ‘Full Model of Football’. Simon Austin. Training Ground Guru. February 2023.
• Stats, Scouting and Smart Coaching: How Toulouse Exceed Expectations. Adam White. The Guardian. February 2023.
• The Athletic Joins MIT’s Sloan Sports Analytics Conference — Part One. John Muller. The Athletic. March 2023.
• Who Is the Best Men’s Player in World Soccer Right Now? We Crunched the Numbers. Ryan O’Hanlon. ESPN. March 2023.
• Can Computers Teach Us How to Counter-Attack?. John Muller. The Athletic. March 2023.
• The Woman Who Uses Big Data to Help Win Soccer Games. Armando Quesada Webb. El País. April 2023.
• Mladen Sormaz: Building a Data Analytics Department. Training Ground Guru. Training Ground Guru. April 2023.
• Mladen Sormaz: Data Analytics in the Multi-Club Model. Training Ground Guru. Training Ground Guru. April 2023.
• AZ Alkmaar Use Brainsfirst Test to Identify Best Young Talent and It Has Helped Them Win UEFA Youth League. Adam Bate. Sky Sports. May 2023.
• Do Football Managers Matter?. John Muller. The Athletic. May 2023.
• The ‘Brain Gym’ Helping Elite Footballers Improve Their Focus. Alex Bysouth. BBC Sport. May 2023.
• Set-Piece Innovations and Busting Myths About Corners: Specialist Set-Piece Coach Andy Parslow Talks Us Through His Role. Adam Bate. Sky Sports. May 2023.
• Mathieu Lacome: How Data Analytics Is Powering Parma’s New Era. Simon Austin. Training Ground Guru. June 2023.
• Lionel Messi: The Evolution of the Greatest Footballer of All Time. John Muller. The Athletic. July 2023.
• Sarah Rudd: The Difference Between Twitter Analytics & Club Analytics. Simon Austin. Training Ground Guru. September 2023.
• The Former Arsenal Analytics Guru and Her Husband Who Are Aiming to ‘Figure Out Football’. John Muller. The Athletic. September 2023.
• Can This Man Make Soccer Smarter?. Rory Smith. The New York Times. October 2023.
• When Moneyball Works Too Well: Milan, Toulouse and What Happens When the Nerds Take Over. Ryan O’Hanlon. ESPN. October 2023.
• SkillCorner: Analysing Centre Forward Off-Ball Runs. SkillCorner. Training Ground Guru. October 2023.
• Ian Graham Helped Fix Liverpool. Can He Fix European Soccer?. Ryan O’Hanlon. ESPN. November 2023.
• How FC Copenhagen Are Leading the Way in Football Brain Training. Simon Austin. Training Ground Guru. November 2023.
• Lee Dykes: Brentford’s Seven Stages of Recruitment. Adam Goodwin. Brentford FC. December 2023.
• Introducing the Athletic’s Match Dashboard: Our Detailed Snapshot of How a Game Unfolds. John Muller. The Athletic. December 2023.
• Lee Mooney: Why Union Saint-Gilloise Performance Versus Cost Is Ridiculous. Training Ground Guru. Training Ground Guru. December 2023.

Podcasts (8)

• David Sumpter - Curiosity-Based Approach to Analytics with David Sumpter and Simon Austin. Training Ground Guru. February 2023.
• Sarah Rudd - Arsenal’s Analytics Pioneer with Sarah Rudd and Simon Austin. Training Ground Guru. September 2023.
• Post Script - Episode 4: The Lost City of Stat-Lantis with John Muller and Tiotal Football. Post Script. March 2023.
• Post Script - Episode 5: Pep Guardiola, Proto-Tactics Blogger with John Muller and Tiotal Football. Post Script. March 2023.
• Post Script - Episode 6: In the Beginning (Again) with John Muller and Tiotal Football. Post Script. August 2023.
• Post Script - Episode 7: Pro Vercelli with John Muller and Tiotal Football. Post Script. November 2023.
• Introducing Brentford’s Recruitment Strategy with Jay Harris and Jon Mackenzie. The Tifo Football Podcast. August 2023.
• What Does a Performance Analyst Actually Do? with Carlon Carpenter and Jon Mackenzie. The Tifo Football Podcast. December 2023.

Events (9)

• MIT Sloan Sports Analytics Conference. Boston, Massachusetts, United States. 3-4 March 2023.
• Opta Pro Forum. London, United Kingdom. 21 March 2023.
• Workshop on Computer Vision in Sports. Vancouver, British Columbia, Canada. 19 June 2023.
• Workshop on Machine Learning and Data Mining for Sports Analytics. Turin, Italy. 12 June 2023.
• MathSport International. Budapest, Hungary. 26-28 June 2023.
• New England Symposium on Statistics in Sports. Harvard University Science Center, Cambridge, Massachusetts, United States. 23 September 2023.
• Training Ground Guru Live. Manchester, United Kingdom. 9-10 October 2023.
• Carnegie Mellon Sports Analytics Conference. Carnegie Mellon University, Pittsburgh, Pennsylvania, United States. 10-11 November 2023.
• Training Ground Guru Big Data. Online. 21 November 2023.

Code repositories (8)

• ballradar. Infer the ball trajectory from the player trajectories in tracking data. Code.
• ETSY. Synchronize event data and tracking data for soccer matches. Code.
• Football-Tracking-Interpolation. Estimate the locations of off-camera players in broadcast tracking data. Code.
• GlickoSoccer. Compute ratings for soccer clubs and soccer leagues. Code.
• implied. Convert between bookmaker odds and implied probabilities for soccer matches. Code. Documentation.
• nwslpy. Access data for the National Women’s Soccer League (NWSL). Code.
• rs-football-3d. Render soccer data in 3D using the Bevy game engine. Code.
• un-xPass. Evaluate the creative abilities of soccer players using StatsBomb 360 data. Code.