Troubleshooting cellular service issues at the per-UE (User Equipment) level is an essential task for cellular providers. However, diagnosing service issues at per-UE level is costly because it requires advanced expertise and in-depth inspection of massive network log data. This paper presents NeTExp, a generic and comprehensive data-driven approach to automatically troubleshoot cellular service issues reported by customers. NeTExp determines whether the root cause of a user-reported service issue is from the network side or the device side through deep neural networks, which extract complex spatial-temporal feature profiles from massive network log data. The system is trained and validated using an extensive period of network and customer care data from a major cellular service provider in United States. We also present a case study on an external event that caused cellular service issues in 2020 to demonstrate the effectiveness of NeTExp on detecting network issues and identifying network-issue-related root causes at per-UE level.

Cellular service carriers often employ reactive strategies to assist customers who experience non-outage related individual service degradation issues (e.g., service performance degradations that do not impact customers at scale and are likely caused by network provisioning issues for individual devices). Customers need to contact customer care to request assistance before these issues are resolved. This paper presents our experience with PACE (ProActive customer CarE), a novel, proactive system that monitors, troubleshoots and resolves individual service issues, without having to rely on customers to first contact customer care for assistance. PACE seeks to improve customer experience and care operation efficiency by automatically detecting individual (non-outage related) service issues, prioritizing repair actions by predicting customers who are likely to contact care to report their issues, and proactively triggering actions to resolve these issues. We develop three machine learning-based prediction models, and implement a fully automated system that integrates these prediction models and takes resolution actions for individual customers. We conduct a large-scale trace-driven evaluation using real-world data collected from a major cellular carrier in the US, and demonstrate that PACE is able to predict customers who are likely to contact care due to non-outage related individual service issues with high accuracy. We further deploy PACE into this cellular carrier network. Our field trial results show that PACE is effective in proactively resolving non-outage related individual customer service issues, improving customer experience, and reducing the need for customers to report their service issues.