INBI: An Improved Network-Based Inference Recommendation Algorithm

Personal recommendation based on bipartite network has gained sustained attention in recent years due to its performance outperforms the traditional collaborative filtering approach, and it is rapidly becoming an important and promising technology for constructing recommender systems. Current viewpoint is focusing on improving precision of the algorithm. In this paper, we present an improved network-based inference(INBI) personal recommendation algorithm which combines weighted bipartite network with a tunable parameter to depress high-degree nodes and sets the value equals to 0.8. Using the practical data set obtained from GroupLens website to evaluate the performance of the proposed algorithm, we performed a series of experiments. The experimental results reveal that it can yield better recommendation accuracy and has higher hitting rate than collaborative filtering(CF), network-based inference(NBI) and weighted network-based inference(NBIw).