NEURAL NETWORK MODEL DEVELOPMENT FOR PATH LOSS PREDICTION IN EVOLVING COMMUNICATION TECHNOLOGIESThe study addresses the necessity for precise path loss prediction in wireless communication design, advocating for data-driven methodologies over conventional models, particularly in the context of dynamic signal variations in advanced 5G technologies. Employing a robust data-driven model based on neural network architecture, the research explores vital parameters to train a multi-layered neural network. Correlation analyses highlight significant associations, emphasizing the impact of environmental conditions and path characteristics on path loss. The proposed model, trained over 150 epochs with three layers, demonstrates superior performance in Mean Absolute Error, Mean Squared Error, and Root Mean Squared Error compared to traditional models. Specifically, it outperforms Okumura-Hata, Costa 231, and Egli models with notable accuracy metrics. Leveraging TensorFlow and Python, the study advances our understanding of parameter-path loss relationships in 5G wireless communication, offering insights for optimized network design and resource allocation. The research pioneers a simulation-based approach using neural networks for path loss prediction, showcasing heightened accuracy and reduced estimation errors. Future directions include exploring advanced machine learning algorithms and assessing the influence of technologies like 5G on path loss prediction.