![]() ![]() ![]() |
![]() |
|
|
![]() ![]() ![]() ![]() ![]() |
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Return to Agents In this paper we propose an agent-based hierarchical clustering technique operating on both user profiles and e-commerce sites. We show, by designing a number of appealing applications, how exploitation of such hierarchies can really benefit both customers and vendors in their activity. As a support for the customer, we provide a categorization of sites of interest as she/he perceives them, and also dynamic e-commerce portal personalization. As a support for the vendor, we design a categorization of customers directly supporting knowledge discovery on customer behavior. ![]() DiSC'03 © 2003 Association for Computing Machinery |