Trust Relationship Prediction in Alibaba E-Commerce Platform

This paper introduces how to infer trust relationships from billion-scale networked data to benefit Alibaba E-Commerce business. To effectively leverage the network correlations between labeled and unlabeled relationships to predict trust, we formalize trust into multiple types and propose a graphical model to incorporate type-based dyadic and triadic correlations, namely e-Trust. We also present a fast learning algorithm in order to handle billion-scale networks. we propose an efficient learning algorithm method by local learning and global inference. Systematically, we evaluate the proposed methods on four different genres of datasets with labeled trust relationships: Alibaba, Epinions, Ciao and Advogato. Experimental results show that the proposed methods achieve significantly better performance than several comparison methods ( $+1.7-32.3\%\;\text{by accuracy}; p ). Most importantly, when handling the real large networked data with over 1,200,000,000 edges (Ali-large), our method achieves 2,000X speedup to infer trust relationships, comparing with the traditional graph learning algorithm.