From Network Experience to Subscriber Retention: An Explainable AI Framework for Mobile Operators
2026-06-03 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors created a system to predict when mobile phone users might stop using their service, called subscriber churn. They used smart computer methods, like explainable AI and machine learning, to analyze real data from a very large mobile operator. Their findings show that how good the user's experience is (QoE) gives better clues about churn than just looking at basic network data. They suggest focusing on user experience metrics can help telcos better understand and prevent churn. They also discuss ideas for improving the prediction and how to use it in real operations.
subscriber churnmobile operatorsmachine learningexplainable artificial intelligencequality of experiencetelecommunicationsnetwork metricsdata-driven analyticspredictive modelingoperational deployment
Authors
Faris B. Mismar, Abdol Saleh, Ivan Maxmillian Putra Pasaribu, Suhelmy Syaifuddin
Abstract
This article presents a framework for the prediction of subscriber churn in mobile operators also known as telecommunication operators (or telcos). This framework covers relevant aspects of data-driven approaches using explainable artificial intelligence and machine learning. To demonstrate the robustness of the framework, we implement it on real data from one of the globally leading telcos with tens of millions of subscribers and show results and actionable insights confirming the usefulness and longevity of the framework. Our results suggest that subscriber quality of experience (QoE) indicators provide stronger churn signals than traditional network counters alone, reinforcing the need for QoE-centric analytics in modern operations in telcos. We conclude with future research directions for improving churn predictability and operational deployment.