Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Item Recommendation for Emerging Online Businesses / 3797
Chun-Ta Lu, Sihong Xie, Weixiang Shao, Lifang He, Philip S. Yu

Nowadays, a large number of new online businesses emerge rapidly. For these emerging businesses, existing recommendation models usually suffer from the data-sparsity. In this paper, we introduce a novel similarity measure, AmpSim (Augmented Meta Path-based Similarity) that takes both the linkage structures and the augmented link attributes into account. By traversing between heterogeneous networks through overlapping entities, AmpSim can easily gather side information from other networks and capture the rich similarity semantics between entities. We further incorporate the similarity information captured by AmpSim in a collective matrix factorization model such that the transferred knowledge can be iteratively propagated across networks to fit the emerging business. Extensive experiments conducted on real-world datasets demonstrate that our method significantly outperforms other state-of-the-art recommendation models in addressing item recommendation for emerging businesses.