This study investigates the use of neural networks to identify and categorize player formations in sports, aiming to enhance tactical analysis and decision-making. High-resolution match footage is collected and meticulously labeled to identify player positions, forming the basis for training a convolutional neural network (CNN). The network is designed to recognize various player formations with high accuracy by applying sophisticated object detection algorithms. The model achieves promising results across common formations. Precision, recall, and F1 scores further demonstrate its effectiveness, indicating reliable classification even under varying conditions. These outcomes provide valuable insights for analysts and coaches, offering a robust tool to enhance strategic planning and improve team performance. Future work will focus on refining the model's accuracy, expanding the dataset, and incorporating real-time analysis capabilities to advance tactical decision-making in competitive sports.