A Users Clustering Algorithm for Group Recommendation
Chen Zhang, Jing Tao Zhou, Weifeng Xie · 2016
Our group recommender system was targeted at a scenario that requires the adoption of group recommendation techniques to conserve computational resources. The profile aggregation strategy was used in our work to implement this group recommendation system. Key to our work, user clustering is also the first step of our work. The accuracy of user clustering could be improved once we processed the data set by the SVD (Singular Value Decomposition) algorithm. The data set in this experiment was 1M user rating data available from MovieLens. According to the metric we used for evaluating the quality of user clustering, we discovered that the bisecting K-means algorithm outperformed the DBSCAN algorithm on the dataset within the experimental settings.