Cellular traffic prediction is one of the key research areas for telecom companies to achieve resource allocation and scheduling; also big data plays an important part in cellular prediction, as traffic prediction requires traffic involving thousands of cells. Furthermore, recent research shows the great potential of adopting the deep learning domain to predict traffic. However, training deep learning models for various prediction tasks is considered a critical task due to various reasons. This research work develops Multi-Layer Hybrid Network (MLHN) for network traffic prediction and analysis; MLHN comprises the three distinctive networks for handling the different inputs for custom feature extraction. Furthermore, an optimized and efficient parameter-tuning algorithm is introduced to enhance parameter learning. MLHN is evaluated considering the “Big Data Challenge” dataset considering the Mean Absolute Error, Root Mean Square Error and R^2 as metrics; furthermore, MLHN efficiency is proved through comparison with the state-of-art approach.