Deriving a negotiation decision function for software agents in electronic commerce

Abstract

With software agents, routine tasks have been automated and hence human involvement has been reduced to a certain extent. However, most of agents have assisted with only a few steps in the multi-steps process of electronic transactions. To help users with the major steps in the electronic transactions, it is necessary for software agents to persuade their negotiation parties to act in particular ways. While negotiations come in many shapes and forms, this thesis focuses on a particular class of negotiation, competitive business environment based negotiation. To negotiate with other parties in this context, autonomous agents consider environmental variables - the number of competitors, the number of negotiation parties, the maximum time by which they must finish their jobs, and user``s preferences. However, previous negotiation decision functions for the automated negotiation have used only time or the static number of negotiating parties as criteria of negotiation, although competitive business environment should include potential competitors who can snatch negotiation parties away. Therefore, this thesis attempts to evaluate the performance of a negotiation decision function that considers the potential competitors in competitive market environment as well as that of a negotiation decision function that does not. For this evaluation, this thesis adopts the electronic marketplace as an application domain because many buyers and sellers compete for limited resources in the marketplace.