Many research papers on tennis match prediction use a hierarchical Markov Model. To predict match outcomes, this model requires input parameters for each player`s serving ability. While these parameters are often computed directly from each player`s historical percentages of points won on serve and return, doing so fails to address bias due to limited sample size and differences in strength of schedule. In this paper, we explore a handful of novel approaches to forecasting serve performance that specifically address these limitations. By applying an Efron-Morris estimator, we provide a means to robustly forecast outcomes when players have limited match data over the past year. Next, through tracking expected serve and return performance in past matches, we account for strength of schedule across all points in a player`s match history. Finally, we demonstrate a new way to synthesize historical serve data with the predictive power of Elo ratings. When forecasting serve performance across 7,622 ATP tour-level matches from 2014-2016, all three of these proposed methods outperformed Barnett and Clarke`s standard approach.
© Copyright 2021 Journal of Sports Analytics. IOS Press. Kaikki oikeudet pidätetään. / Kääntänyt https://www.DeepL.com/Translator