Group CRM

Abstract

The structure of customer communication network provides us a natural way to understand customers' relationships. Traditional customer relationship management (CRM) methods focus on various customer profitability models, and they are short of ways to understand the social interactions. Graph mining and social network analysis provide ways to understand the relationships between customers, and there are already a few applications in CRM using these methods. To transform the traditional CRM methods from individuals to social groups, we propose a novel technical framework (GCRM) to manage the social groups in massive telecom call graphs. Our framework is based on a series of newly emerged methods for social network analysis, such as group detecting, group evolution tracking and group life-cycle modeling in telecom applications. We analyze the relationships between social groups and propose a method to find potential customers in these groups. To evaluate GCRM, we present a comprehensive study to explore the group evolutions in real-world massive telecom call graphs. Empirical results show that by taking this framework, analysts can gain deeper insights into the communication patterns of social groups and their evolutionary patterns which makes the management of these social groups much easier in real-world telecom applications.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 40 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.