Trading in open marketplace using trust and risk

In this paper, we propose buying and selling models for agents to trade in the open multi-agent marketplace. Unlike auctions, we take into account of the fact that agents trading in such open environments has to maximize their profits and at the same time, protect themselves from fraud and deception. We attempt to address this issue by incorporating the element of trust and risk management into our proposed buying and selling model. During buying, agents learn to select their partners based on the trustworthiness of the potential partner as well as its personal risk attitude. During selling, agents learn to increase the chances of winning a deal by adjusting their profit rate, which is a measure that considers both trust and risk. The novelty of this proposal is that it ensures agents continuing to seek maximum expected utility in a dynamic trading environment. Our experimental results confirm the feasibility of our approach.

[1]  Vladimiro Sassone,et al.  A formal model for trust in dynamic networks , 2003, First International Conference onSoftware Engineering and Formal Methods, 2003.Proceedings..

[2]  Joan Feigenbaum,et al.  KeyNote : Trust management for public-key infrastructures. Discussion , 1999 .

[3]  Ling Liu,et al.  A reputation-based trust model for peer-to-peer e-commerce communities , 2003, EEE International Conference on E-Commerce, 2003. CEC 2003..

[4]  Munindar P. Singh,et al.  An evidential model of distributed reputation management , 2002, AAMAS '02.

[5]  Sven Koenig,et al.  Risk-averse auction agents , 2003, AAMAS '03.

[6]  Audun Jøsang,et al.  Analysing the Relationship between Risk and Trust , 2004, iTrust.

[7]  J. Neumann,et al.  Theory of games and economic behavior , 1945, 100 Years of Math Milestones.

[8]  R. Gardner.  Games for business and economics , 1994 .

[9]  Sotirios Terzis,et al.  Engineering Trust Based Collaborations in a Global Computing Environment , 2004, iTrust.

[10]  Giorgos Zacharia,et al.  Trust management through reputation mechanisms , 2000, Appl. Artif. Intell..