This study aims to classify the acceptance of microstrip patch antennas that operates at 2.45 GHz, based on antenna efficiency and gain using advanced machine learning techniques. The primary objective is to develop a reliable classification method for evaluating microstrip patch antenna performance by analyzing key parameters such as ground plane length, ground plane width, feedline length, feedline width, patch width and patch length obtained from CST simulations. Additionally, the study assesses performance metrics including realized gain, radiation efficiency, and total efficiency within the frequency range of 2–3 GHz. Employing three machine learning algorithms—Support Vector Machine (SVM), Decision Tree, and k-Nearest Neighbors (k-NN)—the SVM model achieved the highest accuracy of 97.3%. These findings underscore the potential of machine learning to significantly improve the optimization and classification of antenna designs. Followingly, a graphical user interface (GUI) is created to allow engineers to easily input antenna dimensions and receive an estimate of acceptance. Classifying antennas using machine learning techniques allows engineers to reduce the time required for antenna optimization and classification, hence increasing the efficiency and accuracy of antenna performance evaluation.