Flexible Defense Succeeds Creative Attacks!—A Simulation Approach Based on Position Data in Professional Football
- 1 German University of Sport Science, Cologne, Germany
- 2 German University of Sport Science, Cologne, Germany
- 3 University of Mainz, Mainz, Germany
Abstract
Introduction : The key to success is finding the perfect mixture of tactical patterns and sudden breaks of them, which depends on the behavior of the opponent team and is not easy to estimate by just watching matches. According to the specific tactical team behavior of “attack vs. defense” professional football matches are investigated based on a simulation approach, professional football matches are investigated according to the specific tactical team behavior of “attack vs. defense.” Methods: The formation patterns of all the sample games are categorized by SOCCER © for defense and attack. Monte Carlo-Simulation can evaluate the mathematical, optimal strategy. The interaction simulation between attack and defense shows optimal flexibility rates for both tactical groups. Approach: A simulation approach based on 40 position data sets of the 2014/15 German Bundesliga has been conducted to analyze and optimize such strategic team behavior in professional soccer. Results: The results revealed that both attack and defense have optimal planning rates to be more successful. The more complex the success indicator, the more successful attacking player groups get. The results also show that defensive player groups always succeed in attacking groups below a specific planning rate value. Conclusion: Groups are always succeeding. The simulation-based position data analysis shows successful strategic behavior patterns for attack and defense. Attacking player groups need very high flexibility to be successful (stay in ball possession). In contrast, defensive player groups only need to be below a defined flexibility rate to be guaranteed more success.
- Memmert, D. and Raabe, D. (2018) Data Analytics in Football: Positional Data Collection, Modelling and Analysis. Taylor & Francis Inc., London. https://doi.org/10.4324/9781351210164
- Wellman, M.P. (2006) Methods for Empirical Game-Theoretic Analysis. Association for the Advancement of Artificial Intelligence, Menlo Park, 1552-1556.
- Tuyls, K., Omidshafiei, S., Muller, P., Wang, Z., Connor, J., Hennes, D., et al. (2021) Game Plan: What AI Can Do for Football, and What Football Can Do for AI. Journal of Artificial Intelligence Research, 71, 41-88. https://doi.org/10.1613/jair.1.12505
- Lowe, Z. (2013) Lights, Cameras, Revolution.
- Maksai, A., Wang, X. and Fua, P. (2016) What Players Do with the Ball: A Physically Constrained Interaction Modeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 972-981. https://doi.org/10.1109/CVPR.2016.111
- Le, H. M., Yue, Y., Carr, P. and Lucey, P. (2017) Coordinated Multi-Agent Imitation Learning. International Conference on Machine Learning, New York, 19-24 June 2016, 1995-2003.
- Le, H.M., Carr, P., Yue, Y. and Lucey, P. (2017) Data-Driven Ghosting Using Deep Imitation Learning. MIT Sloan Sports Analytics Conference, Boston, 3-4 March 2017, 1-15.
- Perl, J. and Memmert, D. (2018) Soccer: Process and Interaction. In: Baca, A. and Perl, J., Eds., Modelling and Simulation in Sport and Exercise, Routledge, Abingdon, 73-94. https://doi.org/10.4324/9781315163291-4
- Perl, J. and Memmert, D. (2018) Key Performance Indicators. In: Baca, A. and Perl, J., Eds., Modelling and Simulation in Sport and Exercise, Routledge, Abingdon, 146-166. https://doi.org/10.4324/9781315163291-8
- Memmert, D. and Rein, R. (2018) Match Analysis, Big Data and Tactics: Current Trends in Elite Soccer. German Journal of Sports Medicine/Deutsche Zeitschrift für Sportmedizin, 69, 65-72. https://doi.org/10.5960/dzsm.2018.322
- Perl, J. (2018) Formation-Based Modelling and Simulation of Success in Soccer. International Journal of Computer Science in Sport, 17, 204-215. https://doi.org/10.2478/ijcss-2018-0012
- Perl, J. Imkamp, J. and Memmert, D. (2021) Key Strictness vs. Flexibility: Simulation-Based Recognition of Strategies and Its Success in Soccer. International Journal of Computer Science in Sport, 20, 43-54. https://doi.org/10.2478/ijcss-2021-0003