Ultra accurate personalized recommendation via eliminating redundant correlations

Abstract

In this paper, based on a weighted projection of bipartite user-object network, we introduce a personalized recommendation algorithm, called the \emph{network-based inference} (NBI), which has higher accuracy than the classical algorithm, namely \emph{collaborative filtering}. In the NBI, the correlation resulting from a specific attribute may be repeatedly counted in the cumulative recommendations from different objects. By considering the higher order correlations, we design an improved algorithm that can, to some extent, eliminate the redundant correlations. We test our algorithm on two benchmark data sets, \emph{MovieLens} and \emph{Netflix}. Compared with the NBI, the algorithmic accuracy, measured by the ranking score, can be further improved by 23% for \emph{MovieLens} and 22% for \emph{Netflix}, respectively. The present algorithm can even outperform the \emph{Latent Dirichlet Allocation} algorithm, which requires much longer computational time. Furthermore, most of the previous studies considered the algorithmic accuracy only, in this paper, we argue that the diversity and popularity, as two significant criteria of algorithmic performance, should also be taken into account. With more or less the same accuracy, an algorithm giving higher diversity and lower popularity is more favorable. Numerical results show that the present algorithm can outperform the standard one simultaneously in all five adopted metrics: lower ranking score and higher precision for accuracy, larger Hamming distance and lower intra-similarity for diversity, as well as smaller average degree for popularity.

20 pages, 10 figures, 2 tables

References in corpus (8)

• Predicting Missing Links via Local Information
• How to project a bipartite network?
• Heat Conduction Process on Community Networks as a Recommendation Model
• Power-law Strength-Degree Correlation From a Resource-Allocation Dynamics on Weighted Networks
• Effect of initial configuration on network-based recommendation
• Recommendation model based on opinion diffusion
• Personal Recommendation via Modified Collaborative Filtering
• Information Filtering via Self-Consistent Refinement

Cited by in corpus (18)

• Recommender Systems
• Information filtering via biased heat conduction
• Empirical analysis of web-based user-object bipartite networks
• Link prediction via linear optimization
• Network-based recommendation algorithms: A review
• Information filtering via preferential diffusion
• Experimental analyses on 2-hop-based and 3-hop-based link prediction algorithms
• Solving the accuracy-diversity dilemma via directed random walks
• A vertex similarity index for better personalized recommendation
• Strong ties promote the epidemic prevalence in susceptible-infected-susceptible spreading dynamics
• Promoting cold-start items in recommender systems
• A trust-based recommendation method using network diffusion processes
• An improved HeatS+ProbS hybrid recommendation algorithm based on heterogeneous initial resource configurations
• Degree correlation effect of bipartite network on personalized recommendation
• Information filtering in sparse online systems: recommendation via semi-local diffusion
• Improving personalized link prediction by hybrid diffusion
• Information Filtering on Coupled Social Networks
• Predictability of diffusion-based recommender systems