Momentum Prediction of the Tennis Match Flow
DOI: https://doi.org/10.62517/jmpe.202518104
Author(s)
Yuanhan Chen, Hanqi Wang
Affiliation(s)
School of Optoelectronic Engineering and Instrumentation Science, Dalian University of Technology, Dalian, Liaoning, China
Abstract
Sports matches are characterized by dynamic momentum shifts that significantly influence performance and outcomes. There are many researches discussing about how momentum in sports games affects the match flow. This study aims to quantify, evaluate, and predict momentum dynamics in tennis to provide actionable insights for players and coaches. Using data from the 2023 Wimbledon men’s singles, we developed a multi-method framework integrating the Analytic Hierarchy Process (AHP) and fuzzy comprehensive evaluation to assess player performance through weighted indicators such as advantage, skill, error, and emotion. Principal component analysis (PCA) was applied to identify critical momentum metrics, followed by a neural network model to predict momentum swings by analyzing factors like serve performance and error rates. Results revealed that points scored as the server (x₂) emerged as the most influential predictor of momentum shifts, with high correlation coefficients (Pearson >0.99) validating model accuracy. The framework was further tested on French Open data, demonstrating adaptability across venues and genders, with court surface and player gender identified as secondary influencing variables. Momentum fluctuations showed a direct correlation with performance trends, enabling visualization of game flow and strategic recommendations, such as prioritizing serve efficiency and managing errors during neutral phases. The model’s modular design allows extension to other sports by adjusting sport-specific metrics. This study establishes a robust, data-driven approach to harnessing momentum in competitive settings, offering practical tools for optimizing decision-making during critical match phases.
Keywords
Sports Momentum; Tennis Match Flow Prediction; PCA; AHP
References
[1] Iso-Ahola S E, Blanchard W J. Psychological momentum and competitive sport performance: A field study. Perceptual and Motor Skills, 1986, 62(3): 763-768.
[2] Crust L, Nesti M. A review of psychological momentum in sports: Why qualitative research is needed. Athletic Insight, 2006, 8(1): 1-15.
[3] Kimiecik J C, Jackson S A. Optimal experience in sport: A flow perspective. 2002. Kimiecik J C, Jackson S A. Optimal experience in sport: A flow perspective. 2002.
[4] M. Zhao, H. Jiang, B. Qi and J. Yang. Chinese tennis players emotional intelligence theory model construction and scale preparation. Psychological Research, 2024, 17(01): 42-53. DOI: 10.19988/j.cnki.issn.2095-1159.2024.01.005.
[5] Knight G, O' donoghue P. The probability of winning break points in Grand Slam men's singles tennis. European Journal of Sport Science, 2012, 12(6): 462-468.
[6] Newton PK, Keller J B. Probability of winning at tennis I. Theory and data. Studies in Applied Mathematics, 2005, 114(3): 241-269.
[7] Polly R. Davey, Rod D. Thorpe & Clyde Williams (2002) Fatigue decreases skilled tennis performance, Journal of Sports Sciences, 20:4, 311-318, DOI: 10.1080/026404102753576080
[8] DaiZ, Sun C, Zhao L, et al. Assessment of smart learning environments in higher educational institutions: a study using AHP-FCE and GA-BP methods. IEEE Access, 2021, 9: 35487-35500.
[9] Holland S M. Principal components analysis (PCA). Department of Geology, University of Georgia, Athens, GA, 2008, 30602: 2501.
[10] Roane H S, Kelley M E, Trosclair N M, et al. Behavioral momentum in sports: A partial replication with women's basketball. Journal of applied behavior analysis, 2004, 37(3): 385-390.
[11] Mortimer P, Burt W E. Does momentum exist in elite handball?. International Journal of Performance Analysis in Sport, 2014, 14(3): 788-800.
