A platform for electronic commerce with adaptive agents

Abstract

Market research suggests that organisations, in general, have adifferentiation strategy when approaching Electronic Commerce. Thus, in orderto be useful, agent technology must take into account this market characteristic.When extending its application to the negotiation stage of the shoppingexperience, one should consider a multi-issue approach, from which bothbuyers and sellers can profit. We here present SMACE, a layered platform foragent-mediated Electronic Commerce, supporting multilateral and multi-issuenegotiations. In this system, the negotiation infrastructure through which thesoftware agents interact is independent from their negotiation strategies. Takingadvantage of this concept, the system assists agent construction, allowing usersto focus in the development of their negotiation strategies. In particular, andaccording to experiments here reported, we have implemented a type of agentthat is capable of increasing the performance with its own experience, byadapting to the market conditions, using a specific kind of ReinforcementLearning technique.