Using social network knowledge to enhance customer churn prediction
Year: 2016
Type: conference-abstract
Abstract: Customer churn prediction plays a crucial role in Customer Relationship Management (CRM). Early detection whether a customer will leave the company or not, can prevent potential damage to the customer base. Basic churn models do not fully take advantage of the connectivity between customers and mostly consider a limited form of network information. A suitable approach to fully exploit the interrelatedness between customers is provided by probabilistic graphical models that can model the probability to churn by making use of graph structures and probability theory. By analyzing network information in a framework of probabilistic graphical models, knowledge about the connectivity among customers can be exploited to enhance churn prediction.
Authors: Wai Kei Paul Tsang, Dries F. Benoit
Language: English
Subfield: Marketing
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W2964942393