An adaptive recommendation trust model in multiagent system

Abstract

This work presents the design of a trust model to derive recommendation trust from heterogeneous agents. The model is a novel application of neural network in evaluating multiple recommendations of various trust standards with and without deceptions. The experimental results show that 97.22% estimation errors are less than 0.05. The results also show that the model has robust performance when there is high estimation accuracy requirement or when there are deceptive recommendations.