Evaluation of trust in an ecommerce multi-agent system using fuzzy reasoning

Trust is a fundamental concern in large-scale open distributed systems such as multi-agent systems. It lies at the core of all interactions between the entities that have to operate in such uncertain and constantly changing environments. In this paper, an approach is developed for the evaluation of trust using fuzzy reasoning. The approach takes different trust sources into account, thereby minimizing the effect of wrong evaluations. It also incorporates a time factor for the evaluations of trust to address the different weightings of old versus new evaluations. Furthermore, the overall trust calculation consists of a non-linear weighted fuzzy calculation. A case study outlines different steps of the trust evaluation and shows, how the system computes the overall trust value, the reliability of the company, and the reliability of the results.