Echo State Network with SVM-readout for customer churn prediction
Authors:
- 1 November 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 28, 1-5
Abstract
In all customer based industries, customer churn is considered as one of the most important and challenging concerns since it can lead to a serious profit loss. Therefore, developing accurate churn prediction models can significantly help Customer Relationship Management in planning effective retention campaigns and consequently helps in maximizing the profit of the service provider. In this paper, we propose the use of an Echo State Network (ESN) with a Support Vector Machine (SVM) training algorithm for predicting customer churn in telecommunication companies. The proposed approach is trained and tested based on two datasets: the first is a popular online available dataset while the second is obtained from a local service provider. Experiment results show that ESN with SVM readout outperform other popular machine learning models used in the literature for the same customer churn prediction problems.Keywords
This publication has 14 references indexed in Scilit:
- Simple Deterministically Constructed Recurrent Neural Networks2010
- A new learning paradigm: Learning using privileged informationNeural Networks, 2009
- Integrating the voice of customers through call center emails into a decision support system for churn predictionInformation & Management, 2008
- Model of Customer Churn Prediction on Support Vector MachineSystems Engineering - Theory & Practice, 2008
- Learning grammatical structure with Echo State NetworksNeural Networks, 2007
- Minimum mean squared error time series classification using an echo state network prediction model2006
- Modeling reward functions for incomplete state representations via echo state networks2005
- On the modelling of nonlinear dynamic systems using support vector neural networksEngineering Applications of Artificial Intelligence, 2001
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- The Nature of Statistical Learning Theory1995