Exploiting Implicit Trust and Geo-social Network for Recommendation

Recommender system (RS) seeks to predict the rating or preference a user would give to an item, this system often relies on collaborative filtering (CF). CF suffers from the problems of data sparsity, cold start and location insensitive. Existing RSs do not consider the spatial extent of users, we analyze the users' location data from four commercial websites, and conclude that people with close social relationships prefer to purchase in places that are also physically close. State-of-the-art recommendation algorithm TrustSVD extends RS with social trust information, we propose Trust-location SVD (TLSVD) by incorporating the location information and implicit trust into TrustSVD. The improved TLSVD helps to quantitatively analyze the spatial closeness and preference similarity between users. Experimental results indicate that the accuracy of our method is better than other multiple counterparts', especially when active users have location information or few ratings.