Fencing is an activity that requires high physical and kinetic abilities, given the nature of its performance, which relies on speed, accuracy, balance, and the ability to adapt to changing competitive situations. The importance of this sport lies in the need for distinct biokinetic elements that contribute to achieving excellence through precise kinetic responses and complex skills performed under high pressure. The research problem was represented by the absence of precise scientific methods that rely on analyzing biokinetic abilities as an approach to classifying students and directing them toward activities that match their abilities. This negatively impacts the quality of performance and training outcomes. Therefore, this research aims to contribute to building a predictive classification model based on artificial neural networks to classify students according to their biokinetic abilities. This allows for the selection of the most appropriate elements for participation in the foil game and directs the training process effectively. The research aims to identify the most important biokinetic abilities that distinguish high-performing students in fencing, and to design a classification model that helps predict performance levels based on these abilities. It also seeks to provide a database that supports coaches in designing training programs that suit the characteristics of players and contribute to improving their competitive levels. Based on these objectives, the researcher hypothesized the existence of clear differences in biokinetic abilities among students, affecting the accuracy of performance and level of achievement in the fencing game. He also hypothesized that the use of artificial intelligence techniques would provide a more accurate and objective classification compared to traditional methods. The researchers adopted the descriptive approach using a survey method, given its suitability to the nature of the problem and the objectives of the study. This approach enabled the researchers to conduct a precise scientific analysis of the current state of biokinetic abilities among the research sample, and to analyze them in a way that contributes to the construction of an objective classification model that supports the selection and guidance processes in the sport of foil. The study sample was intentionally selected from (70) second-year students at the College of Physical Education and Sports Sciences at the University of Kerbala for the 2024-2025 academic year. The researchers subjected them to physical and kinetic tests aimed at measuring biokinetic abilities related to performance in the foil event. Through analyzing the results, the researchers concluded that there were clear individual differences among students in the level of biokinetic abilities, which was reflected in the quality of skill performance and kinetic response. The results of the artificial neural network model developed by the researchers also demonstrated a high ability to accurately classify students, confirming the effectiveness of this model in predicting performance levels and guiding training. According to the results, the researchers recommend the adoption of artificial intelligence techniques, particularly artificial neural networks, in the selection, evaluation, and training processes, while emphasizing the importance of developing training programs that take into account the classification results. The study also recommends organizing workshops to enhance the efficiency of training personnel in using these modern tools.