Efficient incremental dynamic link prediction algorithms in social network

To enhance customers' loyalty and experience, link prediction in social networks can help service providers to predict the friendship between users in the future, according to the network structure and personal information. However, most of prior studies consider link prediction in the static scenario while ignoring that the social network generally is updated over time. In this paper, to address this problem, we design two efficient incremental dynamic algorithms that can predict the relationship between users according to the updated social network structure. The first one, instead of using classic prediction index, creates a latent space for each node in the network, and adopts the incremental calculation to predict the future links according to the position of each node in the latent space. The second one is a dynamic improved algorithm based on the resource allocation index, which only recalculates updated part of the social network structure instead of the whole social network. Extensive experiments show that our first algorithm has high prediction accuracy while the second algorithm incurs low running time cost at the expense of less prediction accuracy. (C) 2017 Elsevier B.V. All rights reserved.