Trust is a concept taken from social sciences and is considered as a soft security approach that is effective in reducing risk. In this paper, for estimating the trust between unknown nodes, a group-based trust propagation method has been proposed. Most of the conventional trust propagation methods are not applicable for trust evaluation of today\'s large trust graphs. Our trust propagation method is scalable because of using grouping method. For better trust estimation inside group the confidence of trust value have been considered. We also consider two factors Intermediate Group Confidence (IGC) and Group Confidence (GC) for confidence of trust between two groups. To evaluate this method a real large data set of advogato.org is used. Evaluation of accuracy is based on correlation and mean absolute error(MAE). Comparing the proposed method with the Iterative Multiplication method (IMS) results suggests that the correlation and absolute mean error have been improved. In addition, due to the use of groupbased method the speed of the proposed method has been improved.

Keywords