DocumentCode :
3037823
Title :
The Design of Customer Satisfaction Analysis Model Based on Hierarchical Fuzzy System
Author :
Cao, Huiyu ; Liu, Bin ; He, Jianmin
Author_Institution :
Inst. of Economic Manage., Southeast Univ., Nanjing, China
fYear :
2009
fDate :
24-26 July 2009
Firstpage :
484
Lastpage :
488
Abstract :
A new method of constructing customer satisfaction (CS) analysis model is proposed in detail. Based on statistical analysis, reliability analysis, validity analysis and factor analysis of sample data, the hierarchical model of customer satisfaction analysis is designed using the theory of hierarchical rule structure. In such model, the customer satisfaction analysis system is partitioned into seven sub-systems, each of them holds independent functions. After sorting input variables of each subsystem, the rule base is created using the method of fuzzy rule amplification, and then the rule base is optimized by SVD, interpolation and genetic algorithm. The result of test shows the fuzzy system of customer satisfaction analysis constructed in this paper possess good performance.
Keywords :
customer satisfaction; fuzzy reasoning; fuzzy systems; genetic algorithms; interpolation; knowledge based systems; sampling methods; singular value decomposition; sorting; SVD; customer satisfaction analysis model design; factor analysis; fuzzy inference; fuzzy rule amplification method; genetic algorithm; hierarchical fuzzy rule based system; hierarchical rule structure theory; input variable sorting; interpolation; reliability analysis; sample data; statistical analysis; validity analysis; Customer satisfaction; Data analysis; Fuzzy systems; Genetic algorithms; Input variables; Interpolation; Optimization methods; Reliability theory; Sorting; Statistical analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Business Intelligence and Financial Engineering, 2009. BIFE '09. International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-0-7695-3705-4
Type :
conf
DOI :
10.1109/BIFE.2009.116
Filename :
5208838
Link To Document :
بازگشت