Link prediction in weighted network based on reliable routes by machine learning approach

In data mining, link prediction for the networks is one of the areas of greatest interest today. Research achievements of link prediction problem can be applied in many fields such as study genetically transferred diseases, online marketing, e-commerce services, discover the structure of criminal networks, friend request in social networks … However, most of researchers focused on predicting the existence of links in previous studies of link prediction. The predicting weight of links has not been heavily researched. In this paper, we introduce an effective solution for weighted network. We propose a novel learning-based approach to weight prediction. Our approach presents the Topological Similarity Score (TSS) feature combined by six indices (CN, AA, RA, rWCN, rWAA, rWRA) to compute the similarity scores between nodes. We propose to utilize Support Vector Regression (SVR) with TSS feature to predict weights. All experiments were conducted on five data sets: Cel, USAir, Lesmis, ReHall, Netscience. Experimental results show that our approach can increase the weight prediction correlation coefficient by 70% over and reduce the error by 17%, compared to the baseline approach.