A trust aggregation engine that uses contextual

Trust estimation of partner agents is considered a fundamental step in the process of selecting partners. In previous work, we proposed SinAlpha, an agent-based aggregation engine that computes the trustworthiness of candidate partners by aggregating their historical contractual evidences, taking into account important properties of the dynamics of trust. In this paper, we further argue on the benefits of the trust dynamics, and we describe the Contextual Fitness component, a new element of our computational trust system that brings contextual information into the trust loop, by relating the estimated trustworthiness of partners to the specific current business situation. Experimental results show that such an approach significantly improves partners selection, due to its ability in detecting the flaws of the target population, even when the available historical evidences are scarce.