This paper presents three supervised regression based machine learning approaches to characterize the performance of a 2D array antenna with corporate feeding network at 6 5 GHz based on its design attributes. Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM) models are developed with their respective architecture and compared based on their performance metrics. The regression coefficient (R) represents the prediction accuracy, ranges from 0.93-0.99 for all performance parameters such as the reflection coefficient, the radiation pattern, and efficiencies of each model developed.