A METHOD FOR TELECOM USER PORTRAIT MODELING

DOI

10.2991/fmsmt-17.2017.231How to use a DOI?

Keywords

User portrait, K-means algorithm, User behavior

Abstract

In the era of big data, it is an important means to building user portraits and helping enterprises to implement precise marketing through comprehensive analysis of multidimensional data. Aiming at the problem of lacking detailed mining analysis and one-sided user attribute analysis, a method for modeling user portraits is proposed. On the basis of user's fact label, this method adopts the optimized K-means algorithm to extract the user's hidden label in order to fully describe the user behavior characteristics. The application results show that the modeling method can effectively extract the implicit information of users, fully reflect the potential demand of customers, and provide the possibility for accurate push marketing.

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  - Tingting Tang
AU  - Zhenyu Yin
AU  - Yang Zou
PY  - 2017/04
DA  - 2017/04
TI  - A METHOD FOR TELECOM USER PORTRAIT MODELING
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 1175
EP  - 1180
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.231
DO  - 10.2991/fmsmt-17.2017.231
ID  - Tang2017/04
ER  -