Optimal Shot Sequences by Court Position and Player Types
Research and Practical Application with a ready to use shot sequence dashboard
DOI:
https://doi.org/10.51224/SRXIV.233Keywords:
Tennis, Clustering, Tennis Data Science, Tennis Shot Sequence, Tennis Player TypesAbstract
The thesis aimed to find optimal shot sequences using sequential market basket analysis from different court positions using domain expert agreed court tessellations (Court Segments) and for different player types determined by using unsupervised learning (clustering) (Figure 1).
Accurately determining this information can provide benefits to coaches and tennis academies to:
-better setup training for specific players
-be used alongside talent identification models to help nurture players unique game styles fromearly in their development
-scout opponents and strategise game plans
The K-Prototypes clustering algorithm was used to infer player types. The algorithm was selected over other algorithms by a majority of domain experts. The cluster group sizes were determined using the knee/elbow method and the cluster cohesion and separation was assessed using silhouette coefficient testing. Sequential Market Basket Analysis was applied to spatio-temporal data with the player clusters to determine shot sequences, which were then pruned using multi-metric thresholds including support and lift. Shot Sequences were evaluated using a derived weighted per point outcome and compared to various intuitive baselines.
Metrics
References
ITF Federation. Tennis Glossary [Webpage]. London: ITF; 2021 [cited Nov 2021. Available from: https://m.itftennis.com/en/about-us/organisation/tennis-glossary/.
Association UST. Tennis Tactics: Winning Patterns of Play. 1 ed. New York: Human Kinetics; 1996. 236 p.
Reid M, McMurtrie D, Crespo M. Title: The relationship between match statistics and top 100 ranking in professional men’s tennis. International Journal of Performance Analysis in Sport. 2017;10(2):131-8.
Buscombe RM, Ward JM, editors. Talent Identification and Development in Tennis2014.
Piatetsky-Shapiro G. Discovery, Analysis, and Presentation of Strong Rules. Knowledge Discovery in Databases: AAAI/MIT Press; 1991. p. 229-48.
Ivan FV-C, Sebastián AR. Extending market basket analysis with graph mining techniques: A real case. Expert Systems with Applications. 2014;41(4, Part 2):1928-36.
Agrawal R, Srikant R. Fast Algorithms for Mining Association Rules. Proc 20th Int Conf Very Large Data Bases VLDB. 2000;1215.
Wenninger S, Link D, Lames M. Data Mining in Elite Beach Volleyball – Detecting Tactical Patterns Using Market Basket Analysis. International Journal of Computer Science in Sport. 2019;18(2):1-19.
Kamakura WA. Sequential market basket analysis. Marketing Letters. 2012;23(3):505-16.
Weidner D, Atzmueller M, Seipel D. Finding Maximal Non-redundant Association Rules in Tennis Data. 2020. p. 59-78.
Cui Y, Gomez MA, Goncalves B, Sampaio J. Clustering tennis players' anthropometric and individual features helps to reveal performance fingerprints. Eur J Sport Sci. 2019;19(8):1032-44.
Mehaffey EL. The Effect of Teaching selected forehand stances and grips on Tennis achievement by College Men: Indiana University; 1966.
Eng D, Hagler D. A novel analysis of grip variations on the two-handed backhand. 2014.
McHugh ML. Interrater reliability: the kappa statistic. Biochem Med (Zagreb). 2012;22(3):276-82.
Krumer A, Rosenboim M, Shapir O. Gender, Competitiveness, and Physical Characteristics: Evidence From Professional Tennis. Journal of Sports Economics. 2014;17.
Muhamad TA, Golestani F, Razak MRA. Comparison of Open and Closed Stance Forehand Strokes among Intermediate Tennis Players. International Journal of Kinesiology and Sports Science. 2016;4:26-32.
Genevois C, Reid M, Rogowski I, Crespo M. Performance Factors Related to the Different Tennis Backhand Groundstrokes: A Review. Journal of Sport Sciences and Medicine. 2015;14:194-202.
Loffing F, Hagemann N, Strauss B. The Serve in Professional Men's Tennis: Effects of Players' Handedness. International Journal of Performance Analysis in Sport. 2009;9:255-74.
Carboch J. Comparison of game characteristics of male and female tennis players at grand-slam tournaments in 2016. Trends in sport sciences. 2017;4:151-5.
Loffing F, Hagemann N, Strauss B. Left-Handedness in Professional and Amateur Tennis. PloS one. 2012;7:e49325.
Li Y, Wu H. A Clustering Method Based on K-Means Algorithm. Physics Procedia. 2012;25:1104-9.
Chaturvedi A, Green P, Caroll J. K-modes Clustering. Journal of Classification. 2001;18:35-55.
Huang Z. Extensions to the k-Means Algorithm for Clustering Large Data Sets with Categorical Values. Data Mining and Knowledge Discovery. 1998;2(3):283-304.
ji J, Pang W, Zhou C, Han X, Wang Z. A fuzzy k-prototype clustering algorithm for mixed numeric and categorical data. Knowledge-Based Systems. 2013;30:129–35.
Day WHE, Edelsbrunner H. Efficient algorithms for agglomerative hierarchical clustering methods. Journal of Classification. 1984;1(1):7-24.
Preud’homme G, Duarte K, Dalleau K, Lacomblez C, Bresso E, Smaïl-Tabbone M, et al. Head-to-head comparison of clustering methods for heterogeneous data: a simulation-driven benchmark. Scientific Reports. 2021;11(1):4202.
Milligan GW, Cooper MC. A study of standardization of variables in cluster analysis. Journal of Classification. 1988;5(2):181-204.
Umargono E, Suseno J, Gunawan SK. K-Means Clustering Optimization Using the Elbow Method and Early Centroid Determination Based on Mean and Median Formula. 2020.
Wang F, Franco-Penya H-H, Kelleher J, Pugh J, Ross R. An Analysis of the Application of Simplified Silhouette to the Evaluation of k-means Clustering Validity. 2017.
Kaufman L, Rousseeuw P. Finding Groups in Data: An Introduction to Cluster Analysis2009.
Akogul S, Erişoğlu M. A Comparison of Information Criteria in Clustering Based on Mixture of Multivariate Normal Distributions. Mathematical and Computational Applications. 2016;21:34.
Brin S, Motwani R, Ullman JD, Tsur S, editors. Dynamic itemset counting and implication rules for market basket data. SIGMOD '97; 1997.
Zhang T, editor Association Rules. PAKDD; 2000.
Söğüt M. Stature: Does it really make a difference in match-play outcomes among professional tennis players? International Journal of Performance Analysis in Sport. 2018;18:255-61.
Lavoie S. SportsEd TV. 2021. [cited 2021 November 2021]. Available from: https://sportsedtv.com/blog/What-your-forehand-grip-means-for-shot-depth-and-point-of-contact-tennis%C2%A0.
Suprenko M. Biomechanical substantiation of motor and punch action formation in tennis by taking into account the formation of promising skills and abilities. Journal of Physical Education and Sport. 2021;21(01).
Cross R. Men’s tennis vs Women’s tennis. ITF Coaching and Sport Science Review. 2014;a(62).
Reid M, Morgan S, Whiteside D. Matchplay characteristics of Grand Slam tennis: implications for training and conditioning. Journal of sports sciences. 2016;34:1-8.
Antoun R. Women's Tennis Tactics. LTA, editor. London: Human Kinetics Publishers; 2007. 232 p.
Born P, Malejka L, Behrens M, Grambow R, Meffert D, Breuer J, et al. Stroke placement in women’s professional tennis: What’s after the serve? Sport Science. 2021;3:37-45.
Mlakar M, Kovalchik SA. Analysing time pressure in professional tennis. Journal of Sports Analytics. 2020;6:147-54.
Landlinger J, Stöggl T, Lindinger S, Wagner H, Müller E. Differences in ball speed and accuracy of tennis groundstrokes between elite and high-performance players. European Journal of Sport Science. 2012;12(4):301-8.
Gale-Watts A, Nevill A. From endurance to power athletes: The changing shape of successful male professional tennis players. European Journal of Sport Science. 2016;16:1-7.
Fernandez-Fernandez J, Mendez-Villanueva A, Pluim B. Intensity of tennis match play * Commentary. British journal of sports medicine. 2006;40:387-91; discussion 91.
Loffing F, Hagemann N. On-Court Position Influences Skilled Tennis Players' Anticipation of Shot Outcome. Journal of sport & exercise psychology. 2014;36:14-26.
Bollettieri N. Bollettieri's tennis handbook. Champaign, IL: Human Kinetics; 2001.
Downloads
Posted
Categories
License
Copyright (c) 2022 Shane Liyanage
This work is licensed under a Creative Commons Attribution 4.0 International License.
