The rapid advancement in communication-based based on Artificial Intelligence (AI) applications has driven the next-generation wireless communication networks, with a notable shift from traditional systems. This evolution promises improved coverage and enhanced spectrum efficiency. Leveraging augmented computational processing capabilities and substantial data storage, Machine Learning (ML) concepts, particularly in the domain of antennas, have gained prominence. The optimization of design parameters is a key focus for achieving favourable computational outcomes, surpassing the opportunities for improvement within analytical methodologies that often result in significant computation overheads. This paper explores the utilization of leading AI frontiers such as Machine Learning (ML), Artificial Neural Networks (ANN), and Deep Learning (DL) in wireless communication networks. With a particular emphasis on employing Random Forest machine learning algorithms for the purpose of antenna design and optimization. A comparative analysis between machine learning algorithms and conventional design approaches is presented. This paper specifically investigates the use of the Random Forest machine learning algorithm for the optimization of the Sierpinski fractal carpet antenna. The work carried out assesses the computational feasibility enhancements and the antenna’s application viability in comparison to conventional methods, demonstrating that Random Forest machine learning algorithm yields satisfactory and superior results in antenna design and miniaturization