Applying Modified Fuzzy Neural Network to Customer Classification of E-Business
With the increasing interest and emphasis on customer demands in e-commerce, customer classification is in a crucial position for the development of e-commerce in response to the growing complexity in Internet commerce logistical markets. As such, it is highly desired to have a systematic system for extracting customer features effectively, and subsequently, analyzing customer orientations quantitatively. This paper presents a new approach that employs a modified fuzzy neural network based on adaptive resonance theory to group users dynamically based on their Web access patterns. Such a customer clustering method should be performed prior to Internet bookstores as the basis to provide personalized service. The experimental results of this clustering technique show the promise of our system.
KeywordsRadial Basis Function Neural Network User Interest Customer Behavior Adaptive Resonance Theory Vigilance Parameter
Unable to display preview. Download preview PDF.
- 2.Chen, C.H., Khoo, L.P.: Multicultural factors evaluation on elicited customer requirements for product concept development. In: Proceedings of 16th Interneational Conference for Production Research (ICPR-16), July 29-August 3, pp. 15–23 (2001)Google Scholar
- 11.Baraldi, A., Alpaydm, E.: Simplified ART: a new class of ART algorithms, International Computer Science Institute, Berkeley CA,1998Google Scholar
- 12.Kohonen, T.: Self-Organizing Maps, 2nd Extended edn., Springer Series in Information Sciences, vol. 30, Berlin, Heidelberg, New York (1997)Google Scholar