Document Type: Research Paper
Today, online social networks are very popular due to the possibility of creating relationships between people all over the world. These social networks with possibilities such as friend recommendation generally use local features derived from social graph structure. For friend recommendation, there are different algorithms with local and global approaches. In this paper, we proposed an algorithm with local approach that has a suitable performance compared to other algorithms. In addition, it has an acceptable speed, because of its being local. This new feature was examined on two large social networks: Epinions and Facebook. The research showed that this algorithm can present good predictions and acceptable recommendations.