A new neural network based customer profiling methodology for churn prediction

Authors:
Ashutosh Tiwari;John Hadden;Chris Turner
Affiliations:
Decision Engineering Centre, School of Applied Sciences, Cranfield University, Bedfordshire, UK;Decision Engineering Centre, School of Applied Sciences, Cranfield University, Bedfordshire, UK;Decision Engineering Centre, School of Applied Sciences, Cranfield University, Bedfordshire, UK
Venue:
ICCSA'10 Proceedings of the 2010 international conference on Computational Science and Its Applications - Volume Part IV
Year:
2010

Citing 3
Cited 0

A Data Mining Approach for Retailing Bank Customer Attrition Analysis

Applied Intelligence
Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques

Expert Systems with Applications: An International Journal
Two-level model of customer retention in the US mobile telecommunications service market

Telecommunications Policy

Quantified Score

Hi-index	0.00

Visualization

Abstract

Increasing market saturation has led companies to try and identify those customers at highest risk of churning. The practice of customer churn prediction addresses this need. This paper details a novel approach and framework for customer churn prediction utilising a Neural Network (NN) approach. The methodology for customer churn prediction describes a predictive approach for the identification of customers who are most likely to churn in the future. This is a departure from current research into customer churn which tries to predict which customers are most likely to instantaneously churn. A real life case study from industry is presented here to illustrate this approach in practice. Future research will include the enhancement of this approach for more accurate modelling of collective systems.