In recent years, Machine Learning (ML) has become a crucial and promising tool for forecasting and solving a wide range of complex problems. The rapid development of machine learning is closely linked to technological advancements and has also driven the growth of the AI community and open-source tools (e.g., TensorFlow, Keras, PyTorch, fast.ai). This enables researchers to deploy and apply machine learning algorithms more effectively. This paper provides an overview of mobile network traffic at BTS stations, conducted from a data-driven perspective, focusing on extracting and transforming data into information that serves production and business purposes within mobile networks, as well as describing the characteristics of user traffic. The authors used the Google Colab environment to analyze network time statistics to determine traffic in each area. Leveraging large volumes of information helps improve mobile network performance and address various issues (e.g., anomaly detection) that may impact network infrastructure. The study's findings contribute to addressing certain practical challenges in deployment, optimization, resource allocation, and energy savings for mobile networks.