Development of motivation model towards anthropometric, soccer skills, maturity and physical fitness using machine learning

Research in soccer has shown that players' technical, tactical, physical, and psychological abilities are required to meet the requirements of the competition. This study uses machine learning to develop a motivation model based on anthropometric, fitness, and soccer skills. Data were collected from 223 young Malaysian athletes consisting of Malaysia's Sport School soccer athletes who play in various positions (defender, midfielder and forward) aged 13 to 17 years old who participated in this study. Athletes are
required to complete the study's instrument, which consists of the anthropometric component test, Task and Ego Orientation in Sport Questionnaire (TEGSQ), technical skill component and physical fitness test. Data analysis was carried out using hierarchical agglomerative cluster analysis (HACA) and discriminant analysis (DA). Hierarchical agglomerative cluster analysis is used to divide groups according to their homogenous psychological attributes of the athletes and discriminant analysis used for determining the differences in player performance. Three groups formed and successfully discriminated three groups on 13 independent variables with 79.82% (forward stepwise) total variance resulting with Machine Learning method (Artificial Neural Network) 67 athletes predicted with potential. A group tends to have the taller player because of the highest significance in height variables than others. From the result, all groups show their characteristics with unique attributes and need to intervene to characterize their training program based on the group's performance.