A brokering protocol for agent-based e-commerce

The paper explores issues of engineering agents that partially automate some of the activities of information brokering in e-commerce. In particular, it focuses on addressing the problem of connecting buyers and sellers. An algorithm that uses multiple criteria to match buyers and sellers based on prespecified user profiles was devised and implemented. The process of matching and connecting buyers and sellers are divided in four stages: selection, evaluation, filtering and assignment. Ideas of the approach of connection are realized in a testbed on securities trading consisting of a society of information agents (a broker agent, a recommendation agent and a record agent) and trading agents (buyer and seller agents) that communicates via a blackboard database. In addition, an information brokering protocol was devised and implemented to structure the interactions and information exchange among agents in the testbed. A series of experiments that were carried out showed favorable results in executing the protocol.