A multi-agent system for e-insurance brokering

• Type: Article in International Scientific Journal
• Date: 2002

Authors

I. Nogueira (Author) Other; Eugénio Oliveira (Author) FEUP

Journal

Title: Lecture Notes in Computer Science

Vol. 2592

Pages: 263-282

ISSN: 0302-9743

Publisher: Springer Nature

Indexing

ISI Web of Knowledge - 1 Citation

Scientific classification

FOS: Natural sciences > Computer and information sciences

Other information

Authenticus ID: P-000-QT6

DOI: 10.1007/3-540-36559-1_20

Abstract (EN): Agent-based systems suitable for dealing with applications where the environment is both dynamic and populated with competitors demand for sophisticated characteristics including adaptation, negotiation and coordination. In this paper we propose an agent-mediated insurance brokering system using a flexible negotiation model that includes multi-attribute bidding as well as some kind of learning capabilities. Moreover, in the core of the provided brokering facility, we are using conceptual clustering procedures as an approach to better match customers and insurance product offers providing a valuable add-on to both customer's and sellers' sides. Intelligent agents engage themselves in a negotiation process by exchanging proposals and counter-proposals trying to convince opponents to modify their bidding values. We are now developing a Java based multi-agent infrastructure specifically dedicated to the insurance e-commerce domain, exploiting Toshiba's Bee-gent framework. For both acceptability and generalisation purposes, XML (including appropriate ontology-based messages) has been chosen as our agent communication format.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 20