The Research of Online Shopping Customer Churn Prediction Based on Integrated Learning

DOI

10.2991/mecae-18.2018.133How to use a DOI?

Keywords

customer churn, artificial neural network,support vector machine.

Abstract

The prediction of customer churn is an important research direction of customer churn management. In this paper, take the non-contract scenario of online shopping customers as an example, select transaction data of a domestic e-commerce website for empirical research. On the basis of the single model-BP neural network and support vector machine, apply the integrated learning theory to the online shopping customer classification. The empirical results show that the combined forecasting model has a significant improvement in the hit rate, coverage rate, accuracy rate and lift degree, and so on. In order to effectively identify different types of lost customers, use the RFM theory to classify the different value of the lost customers, thus implementation the strategy of customer churn retention.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Guoen Xia
AU  - Qingzhe He
PY  - 2018/03
DA  - 2018/03
TI  - The Research of Online Shopping Customer Churn Prediction Based on Integrated Learning
BT  - Proceedings of the 2018 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2018)
PB  - Atlantis Press
SP  - 259
EP  - 267
SN  - 2352-5401
UR  - https://doi.org/10.2991/mecae-18.2018.133
DO  - 10.2991/mecae-18.2018.133
ID  - Xia2018/03
ER  -