This paper investigates the classification of Circular Microstrip patch antenna based on the radiation pattern variations through machine learning technique. The objective of this research is to develop a machine learning algorithm for assessing circular microstrip patch antenna performance based on their radiation pattern characteristics and to classify it accordingly. Various machine learning algorithms, including Neural Networks, Decision Trees, and Support Vector Machines (SVM), are employed to classify the radiation patterns and evaluate antenna acceptance. The study encompasses the design and simulation of circular microstrip patch antennas followed by data normalization and model training in MATLAB. Followingly, various models were trained to predict the accuracy level. Among the evaluated classifiers, SVM exhibited the highest precision score of 97.4%, establishing it as the preferred choice for this task. The findings demonstrate that the proposed method can accurately classify circular microstrip patch antennas. This research advances the field of design and development of antenna to become more efficient.