An optimized process neural network model

Authors:
Guojie Song;Dongqing Yang;Yunfeng Liu;Bin Cui;Ling Wu;Kunqing Xie
Affiliations:
School of Electronic Engineering and Computer Science, Peking University, Beijing, China and National Laboratory on Machine Perception, Peking University, Beijing;School of Electronic Engineering and Computer Science, Peking University, Beijing, China;Computer Center of Peking University, Beijing;School of Electronic Engineering and Computer Science, Peking University, Beijing, China;School of Electronic Engineering and Computer Science, Peking University, Beijing, China;National Laboratory on Machine Perception, Peking University, Beijing
Venue:
DASFAA'07 Proceedings of the 12th international conference on Database systems for advanced applications
Year:
2007

Citing 4
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
An application of support vector machines for customer churn analysis: credit card case

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we proposed an optimized process neural network based on fourier orthogonal base function, which can deal with both static value and time-varied continuous value simultaneously. To further improve its performance, we optimize the network topological structure, which adopts fourier expansion based preprocessing. Experiments based on the real datasets show that our proposed churn predictionmethod has bettermaneuverability and performance.Most important of all, our method has been used in real applications in China Mobile which is the major telecommunication company of the world.