Serve strategy in professional women's doubles tennis- a data-driven perspective

被引:0
|
作者
Vives, Fernando [1 ]
Lazaro, Javier [2 ]
Guzman, Jose Francisco [1 ]
Crespo, Miguel [2 ]
Martinez-Gallego, Rafael [1 ]
机构
[1] Univ Valencia, Valencia, Spain
[2] Int Tennis Federat UK, London, England
关键词
racquet sports; machine learning; strategy; sport analytics; serve; RANKING; TOP;
D O I
暂无
中图分类号
F [经济];
学科分类号
02 ;
摘要
This study aimed to identify the key variables that influence the effectiveness of the first serve in women's doubles matches using a deep learning training model. A total of 4939 first serves by 145 players from Billie Jean King Cup matches were classified according to their effectiveness. Data from the Hawk-Eye system were filtered and processed to obtain descriptive statistics of the spatio-temporal predictor variables and then to calculate the most important variables for first serve effectiveness. The angle of the serve as the feature that gained more relevance, along with the speed and distance from the bounce to the sidelines, regardless of the side from which the serve was made. The training model showed novel results, identifying that the values of the serve angle between 5.5 degrees-8.7 degrees increased the effectiveness from 22.2% to 48.5% on the Deuce side and from 17.3% to 45.7% on the Advantage side. These findings align with existing research on men's professional tennis singles and offer valuable insights into strategic and coaching approaches. The insights gathered from this study are poised to enhance training methodologies and match-day strategies, providing a strategic edge in serve selection during competitive play.
引用
收藏
页码:955 / 962
页数:8
相关论文
共 50 条
  • [41] A bias-variance perspective of data-driven control
    Colin, Kevin
    Ju, Yue
    Bombois, Xavier
    Rojas, Cristian R.
    Hjalmarsson, Hakan
    IFAC PAPERSONLINE, 2024, 58 (15): : 85 - 90
  • [42] Data-driven laboratory stewardship: an implementation science perspective
    McCleary, Nicola
    Brehaut, Jamie
    Grimshaw, Jeremy M.
    McCudden, Christopher
    JOURNAL OF LABORATORY AND PRECISION MEDICINE, 2024, 9
  • [43] Professional identity development of English teachers: A data-driven model
    Cosgun, Gamze Erdem
    Savas, Perihan
    REVIEW OF EDUCATION, 2023, 11 (01):
  • [44] Data-driven design of electrocatalysts: principle, progress, and perspective
    Zhu, Shan
    Jiang, Kezhu
    Chen, Biao
    Zheng, Shijian
    JOURNAL OF MATERIALS CHEMISTRY A, 2023, 11 (08) : 3849 - 3870
  • [45] Stability in data-driven MPC: an inherent robustness perspective
    Berberich, Julian
    Koehler, Johannes
    Mueller, Matthias A.
    Allgower, Frank
    2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 1105 - 1110
  • [46] A Data-Driven Perspective on the Hierarchical Assembly of Molecular Structures
    Boninsegna, Lorenzo
    Banisch, Ralf
    Clementi, Cecilia
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2018, 14 (01) : 453 - 460
  • [47] Data-Driven Approach for Systemic Risk: A Macroprudential Perspective
    Barsotti, Flavia
    PROGRESS IN INDUSTRIAL MATHEMATICS AT ECMI, 2022, 39 : 527 - 534
  • [48] Driver cognitive workload estimation: A data-driven perspective
    Zhang, YL
    Owechko, Y
    Zhang, J
    ITSC 2004: 7TH INTERNATIONAL IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, PROCEEDINGS, 2004, : 642 - 647
  • [49] An Automated and Data-Driven Bidding Strategy for Online Auctions
    Jank, Wolfgang
    Zhang, Shu
    INFORMS JOURNAL ON COMPUTING, 2011, 23 (02) : 238 - 253
  • [50] Data-driven techniques in rheology: Developments, challenges and perspective
    Mangal, Deepak
    Jha, Anushka
    Dabiri, Donya
    Jamali, Safa
    CURRENT OPINION IN COLLOID & INTERFACE SCIENCE, 2025, 75