Customer Segmentation for Power Enterprise Based on Enhanced-FCM Algorithm

Customer segmentation is an important topic of customer relationship management and FCM is a common method for customer segmentation. However, FCM is sensitive to outliers and hard to determine the number of clusters. In this paper, we define hierarchical analytical indicators for power customer seg...

Full description

Saved in:
Bibliographic Details
Published inAdvanced Data Mining and Applications pp. 127 - 137
Main Authors Song, Lihe, Zhan, Weixu, Qian, Shuchai, Yin, Jian
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg
SeriesLecture Notes in Computer Science
Subjects
AHP
Clustering
Customer segmentation
FCM
Online AccessGet full text

Cover

More Information
Summary:Customer segmentation is an important topic of customer relationship management and FCM is a common method for customer segmentation. However, FCM is sensitive to outliers and hard to determine the number of clusters. In this paper, we define hierarchical analytical indicators for power customer segmentation, and propose a new algorithm called WKFCM_S2 by combining enhanced-FCM algorithm with the analytical hierarchy process. Experiments on a real customer data set of a power supply enterprise show that the WKFCM_S2 algorithm is more robust to noise and more suitable for applications.
ISBN:9783642355264
3642355269
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-642-35527-1_11