Web-mining for Internet shopping: A web-based business transaction

With the advances in Internet and fast development of E-commerce, Internet shopping is becoming popular and playing an important role in today's business transactions. Such technological innovations have substantially changed the notion of value. To handle huge amount of business information effectively and efficiently, there has been immediate need for an autonomous, mobile and robust system which can offer decision-making support for customers who are looking for the cheapest, the most familiar, or the best-quality product. This paper presents a web-mining approach to Internet shopping. In contrast to the traditional multi-agent systems which use rule-based or case-based process flows to coordinate communications for system automation, we propose a fuzzy neural network to tackle the uncertainties in practical shopping activities such as consumer requirement, product specification, product selection, price negotiation, purchase and delivery, after-sale service and evaluation. The fuzzy neural network provides an automatic and autonomous product classification and selection scheme to support fuzzy decision making by integrating fuzzy logic technology and the Back Propagation Feed Forward (BPFF) neural network. An agent development tool named "Aglet" is used as a programming framework for system implementation. The experimental results demonstrate the efficiency and effectiveness of the proposed approach to web-based business transaction.