Constructing a Gaming Model for Professional Tennis Players Using the C5.0 Algorithm

Abstract

Professional tennis players have their own habits of tactics and play. However, players’ shortcomings can be corrected by constantly practicing professional techniques and by tactical analysis. Therefore, this study aimed to develop a two-stage, expert decision-making system for tennis matches. The first stage consisted in dividing the court area and defining the technical classification of the net. Tennis coaches were invited to assess tennis players’ skills on the competition court, dividing it into 48 areas on both sides of the court centerline and identifying the skills used by the players. In the second stage, a classification model was developed, and the score, hitting habits, and tennis skills of the players, Roger Federer and Rafael Nadal, over 10 matches, played from 2007 to 2019, were analyzed and classified using notational analysis and the C5.0 decision tree algorithm. The results show that the two players’ highest scored techniques were the forehand stroke in the backcourt and the backhand stroke in the half court. Thus, using this expert decision-making system, our data can provide other players with imaginary training objects from two of the top players in the world to be used during training and can allow the accumulation of experience for players through continuous simulation and training analysis.

Determining the tactical and technical level of competitive tennis players using a competency model: a systematic review

“…Two studies investigated game situations in tennis matches, and both were of good methodological quality. The first study ( 64 ) analysed the matches of two elite tennis players based on the assessment of tennis coaches and established a classification model that incorporated the players’ playing status, hitting habits and tennis skills, which formed the basis for the matches in which the notation analysis and decision tree algorithm were used. The study proved that integrated analysis of tennis games at the highest level is possible with the help of modern technologies, which can be used for imaginary training of other players so that players can gain experience through continuous simulation of training and game analysis.…”

“…These methods enable the analysis of a large amount of data on the players’ stroke and movement techniques, the trajectories and landing points of the balls and the general observation of both tennis players during the match. Chang and Qiu ( 64 ) analysed two elite tennis players and, together with tennis experts, developed a decision tree algorithm that took into account game results, hitting habits and tennis knowledge. The use of this decision-making system is a useful tool for comprehensive and detailed analysis as well as a training tool for tennis players to gain experience.…”

Sports Recommender Systems: Overview and Research Issues

“…Chang and Qiu [24] introduce an approach to the inference of decision trees from tennis player strengths and weaknesses, for example, in terms of hitting techniques (forehand, backhand, volley, serve, slide, topspin, and smash), physical condition, and habitual scoring positions. Based on a corresponding dataset, the authors show how to derive a decision tree which can be regarded as a constraint set representing tactics in specific gaming situations.…”

Multitask Multi attention Residual Shrinkage Convolutional Neural Network Personalized Assessment Model of Tennis Teaching Based on Data Mining and Intelligent Recommendation

“…Women who play tennis now focus on efficacy, avoid making unnecessary mistakes. The primary goals are increase winning rate of women's tennis matches, offer suitable counter measures, recommendations for assessing quantitative indicators of tennis match winners, attains exact tennis training execution techniques [19].…”