Churn analysis: Predicting churners

Abstract

Churners have always been a big issue for any service providing company. Churning increases cost of the company as well as decreases the rate of profit. Generally, customer attrition can be identified when they initiate the process of service termination. At the same time, the individuals and the institutions that provide the data residing on the government databases-as well as the agencies who sponsor the collection of such information- are becoming increasingly aware that extend analytical capabilities also furnish tools that threaten the confidentiality of data records. However, using predictive analysis using customers past service usage, service performance, spending and other behavior patterns, the likelihood of whether a customer wants to terminate service can be determined. In this paper, the authors address the issue of churn analysis considering a scenario in which a company owning confidential databases wish to run a churn analysis technique on the union of their databases, without revealing any unnecessary information. The aim of the paper is to predict whether a customer will churn in the near future or not based on the predictive analysis using billing data of a telecom company.

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 — 16 citations exist upstream.

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