This study applies data analytics to LTE network performance data to identify the key drivers of customer experience degradation during peak traffic periods. Using a structured approach combining exploratory data analysis, visualisation, hypothesis testing, correlation, and regression modelling, the analysis demonstrates that network congestion—driven primarily by high resource utilisation and traffic demand—is the dominant factor reducing throughput. A Capacity Stress Framework was developed to identify high-risk cells, enabling targeted, data-driven recommendations for capacity investment to improve network performance and optimise resource allocation.

This study applies data analytics to LTE network performance data to identify the key drivers of customer experience degradation during peak traffic periods. Using a structured approach combining exploratory data analysis, visualisation, hypothesis testing, correlation, and regression modelling, the analysis demonstrates that network congestion—driven primarily by high resource utilisation and traffic demand—is the dominant factor reducing throughput. A Capacity Stress Framework was developed to identify high-risk cells, enabling targeted, data-driven recommendations for capacity investment to improve network performance and optimise resource allocation.

This study applies data analytics to LTE network performance data to identify the key drivers of customer experience degradation during peak traffic periods. Using a structured approach combining exploratory data analysis, visualisation, hypothesis testing, correlation, and regression modelling, the analysis demonstrates that network congestion—driven primarily by high resource utilisation and traffic demand—is the dominant factor reducing throughput. A Capacity Stress Framework was developed to identify high-risk cells, enabling targeted, data-driven recommendations for capacity investment to improve network performance and optimise resource allocation.