A Learning-Enabled Integrative Trust Model for E-Markets

Existing e-markets presumes no deception at agents or employed simple mechanisms to counter-act deception. However, the reality shows agents in e-markets can either cheat or break contacts due to higher benefits elsewhere and is similar to what a human society is. Accordingly, the notion of trust in a human society should be implemented in e-markets. Most of existing researches on trust molded trust theoretically from different views, and hence is not easy to get them deployed in e-markets due to the essence of non-computability. However, current computable trust mechanisms, such as those in eBay and Nextag, uniformly manipulate trust involved in all trading, resulting in complaints about none-differentiable experience. On the other hand, a computable trust model can help the formation of coalitions in e-markets and gain market warfare. In this paper, we present a new computable trust model absorbing major views of trust with which agents in e-markets can better evaluate ones to be possibly traded with before trading processes take place. In this model, trust is characterized with the properties of being computable, individualized, evolutional, represented by scores, and extendable to the computation of coalition trust.