Application of BP neural network algorithm in bank customer hierarchy system
- 10.2991/ifeesm-17.2018.284How to use a DOI?
- Customer hierarchy system,BP neural network,Data mining technology
The ever fierce competition in the financial market has highlighted the importance of maintaining good customer relationship for banks. The Customer Relationship Management (CRM) is built on a layered system and the traditional BP neural network has low speed and accuracy. The paper is an attempt to optimize customer layered system by exploring algorithm in BP neural network to arrive at a more precise customer classification system. Momentum-adaptive learning rate adjustment algorithm is used to improve BP neural network algorithm. Since learning speed will decline with more learning, global search is adopted at high learning speed and as it slows down, local search can yield more accurate results. It not only ensures the speed of each epoch but also pinpoints the optimal. The conclusion shows that improved BP neural network algorithm has enhanced accuracy and efficiency of customer segmentation and formed a valid basis for targeted marketing by commercial banks.
- © 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/).
Cite this article
TY - CONF AU - Guowei Wang AU - Yunting Bai AU - Yu Sun PY - 2018/02 DA - 2018/02 TI - Application of BP neural network algorithm in bank customer hierarchy system BT - Proceedings of the 2017 3rd International Forum on Energy, Environment Science and Materials (IFEESM 2017) PB - Atlantis Press SP - 1560 EP - 1565 SN - 2352-5401 UR - https://doi.org/10.2991/ifeesm-17.2018.284 DO - 10.2991/ifeesm-17.2018.284 ID - Wang2018/02 ER -