The use of adaptive negotiation by a shopping agent in agent-mediated electronic commerce

Abstract

Software agents could help buyers and sellers to combat information overload and expedite specific stages of the online buying process. On the other hand, in a multi-agent system such as an agent-mediated electronic commerce, it is desirable that the agents try to adapt to the environment by learning or by an evolutionary process, thus doing an anticipation of the interaction with the other agents. The paper presents a shopping agent architecture, SmartAgent, whose role is to assist users when doing electronic shopping, in the Internet. The agent has a learning capability implemented by a feed-forward artificial neural network that allows him to model the other agent's negotiation strategy, thus doing an adaptive negotiation in order to make a better deal.