Real-Time Recognition of Calling Pattern and Behaviour of Mobile Phone Users through Anomaly Detection and Dynamically-Evolving Clustering

摘要: In the competitive telecommunications market, information that mobile telecom operators can obtain by regularly analysing their massive stored call logs, is of great interest. Although data be extracted nowadays from phones have been enriched with much information, solely logs give us vital about customers. This usually related calling behaviour customers and it used to manage them. However, analysis these normally very complex because vast stream analyse. Thus, efficient mining techniques need for this purpose. paper, a novel approach analyse detail records (CDR) proposed, main goal extract cluster different patterns or behaviours, detect outliers. The novelty works in real-time using an evolving recursive framework.