Analysis of Call Detail Records for Understanding Users Behavior and Anomaly Detection Using Neo4j

Abstract

Call Detail Records (CDR) is a valuable source of information; it opens new opportunities for mobile operator industries and maximize their revenues as well as it helps the community to raise its standard of living in many different ways. Nevertheless, we need to analyze CDR in order to extract its big value and detect abnormal costumers behaviors to help companies to develop their future plans. However the analysis of CDRs is a very complex process this because it has a huge volume of data. Therefore, In this paper we propose an approach that makes use of Neo4j for automatic analysis of CDRs. To achieve this we transformed the CDR data into neo4j and then we used cypher query language for performing an automatic analysis. A real case study was used to evaluate the proposed approach.