CHAMP: A Prototype for Automated Cellular Churn Prediction

Authors:
Brij Masand;Piew Datta;D. R. Mani;Bin Li
Affiliations:
GTE Laboratories, Waltham, MA. brij@gte.com;GTE Laboratories, Waltham, MA. pdatta@gte.com;GTE Laboratories, Waltham, MA. mani@gte.com;GTE Laboratories, Waltham, MA. bli@gte.com
Venue:
Data Mining and Knowledge Discovery
Year:
1999

Citing 4
Cited 4

Explicitly biased generalization

Computational Intelligence
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The cascade-correlation learning architecture

Advances in neural information processing systems 2
C4.5: programs for machine learning

C4.5: programs for machine learning

Knowledge discovery on customer churn prediction

MATH'06 Proceedings of the 10th WSEAS International Conference on APPLIED MATHEMATICS
Monitoring and backtesting churn models

Expert Systems with Applications: An International Journal
Application of data mining techniques for customer lifetime value parameters: a review

International Journal of Business Information Systems
Reconciling performance and interpretability in customer churn prediction using ensemble learning based on generalized additive models

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe CHAMP (CHurn Analysis, Modeling, and Prediction), anautomated system for modeling cellular customer behavior on a large scale.Using historical data from GTE‘s data warehouse for cellular phone customers, every month CHAMP identifies churn factors for several geographic regionsand updates models to generate churn scores predicting who is likely tochurn within the near future. CHAMP is capable of developing customizedmonthly models and churn scores for over one hundred GTE cellular phonemarkets totaling over 5 million customers.