A Multi-Layer Dynamical Model for Customer Experience Analytics

Today, data collected by service providersnetwork monitoring products can follow individual users' experience in detail, at flow or packet level in real time. However, analytics methods that can translate such information into an intimate, evolving picture of user experience are lacking. In this paper, we provide a layered dynamical model that addresses this problem: to relate low-level network performance metrics to users' perception of the network service and their subsequent actions. Using time-stamped observations from networks, devices, and customer care, we build probabilistic models to link network performance to an inferred state of customer satisfaction, and then to explicit and implicit customer disengagement events. We provide inference algorithms for the model parameters, and report test results on datasets synthesized based on real but incomplete observations. For protecting sensitive private user data, we discuss how popular anonymization techniques such as data masking, encryption, k-anonymization, and differential privacy can be used without interfering with the experience inferences.