Abstract

The need for efficient decentralized recommender systems has been appreciated for some time, both for the intrinsic advantages of decentralization and the necessity of integrating recommender systems into P2P applications. On the other hand, the accuracy of recommender systems is often hurt by data sparsity. In this paper, we compare different decentralized user-based and item-based Collaborative Filtering (CF) algorithms with each other, and propose a new user-based random walk approach customized for decentralized systems, specifically designed to handle sparse data. We show how the application of random walks to decentralized environments is different from the centralized version. We examine the performance of our random walk approach in different settings by varying the sparsity, the similarity measure and the neighborhood size. In addition, we introduce the popularizing disadvantage of the significance weighting term traditionally used to increase the precision of similarity measures, and elaborate how it can affect the performance of the random walk algorithm. The simulations on Movie Lens 10,000,000 ratings dataset demonstrate that over a wide range of sparsity, our algorithm outperforms other decentralized CF schemes. Moreover, our results show decentralized user-based approaches perform better than their item-based counterparts in P2P recommender applications.