Knowledge discovery for adaptive negotiation agents in e-marketplaces

With the increasing popularity of e-marketplaces for B2C and B2B e-commerce, intelligent software agents are promising in improving the effectiveness of these markets by autonomously searching for products and negotiating contracts on behalf of the human decision makers. A large number of research has been conducted to develop negotiation protocols and mechanisms for automated negotiations. However, existing negotiation systems are weak in dealing with incomplete and dynamic negotiation spaces which are common for negotiations in e-commerce. This paper illustrates a novel knowledge discovery method and a probabilistic negotiation decision making mechanism to improve the performance of negotiation agents participating Preprint submitted to Elsevier Science 28 August 2007 in e-marketplaces. Our preliminary experiments show that the probabilistic negotiation agents empowered by knowledge discovery mechanisms are more effective and efficient than the Pareto optimal negotiation agents in simulated e-marketplaces.