A multi-agent system for e-insurance brokering

• Tipo: Artigo em Revista Científica Internacional
• Data: 2002

Autores

I. Nogueira (Autor) Outra; Eugénio Oliveira (Autor) FEUP

Revista

Título: Lecture Notes in Computer Science

Vol. 2592

Páginas: 263-282

ISSN: 0302-9743

Editora: Springer Nature

Indexação

ISI Web of Knowledge - 1 Citação

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da computação e da informação

Outras Informações

ID Authenticus: 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.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 20