Analysis and Application of Broadband Off-grid User Prediction Model Based on Data Mining

DOI

10.2991/mcei-16.2016.70How to use a DOI?

Keywords

Off-grid users; Data mining; Random forest; Prediction model

Abstract

With the fast development of the communication industry in China, the users of a telecom carrier may transfer their business into another better telecom carrier. Therefore, such potential loss may make the telecom carrier more and more challenging.ÿHow to apply data mining technique in the prediction of broadband off-grid users and further the suitable decision to make is an increasingly popular problem. In this paper, a batch of consumer behavior data, i.e., call records and Internet data, are first extracted, transformed and integrated, which are utilized to generate user feature information; then a novel data mining method based on random forest is proposed to build a robust off-grid user prediction model in telecom enterprise and compared with decision tree and support vector machine. The experiments on the real user data of telecom show that the proposed model can efficiently predict most of potential off-grid users in a shorter time. At the same time, it also provides more accurate marketing strategies timely.

Copyright

© 2017, 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  - Juan Zhang
AU  - Xiaoyong Bian
PY  - 2016/12
DA  - 2016/12
TI  - Analysis and Application of Broadband Off-grid User Prediction Model Based on Data Mining
BT  - Proceedings of the 2016 6th International Conference on Mechatronics, Computer and Education Informationization (MCEI 2016)
PB  - Atlantis Press
SP  - 334
EP  - 338
SN  - 1951-6851
UR  - https://doi.org/10.2991/mcei-16.2016.70
DO  - 10.2991/mcei-16.2016.70
ID  - Zhang2016/12
ER  -