Temporal Community-Based Collaborative Filtering to Relieve from Cold-Start and Sparsity Problems

Recommender systems inherently dynamic in nature and exponentially grow with time, in terms of interests and behaviour patterns. Traditional recommender systems rely on similarity of users or items in static networks where the user/item neighbourhood is almost same and they generate the same recommendations since the network is constant. This paper proposes a novel architecture, called Temporal Community-based Collaborative filtering, which is an association of recommendation and the dynamic community algorithm in order to exploit the temporal changes in the community structure to enhance the existing system. Our framework also provides solutions to common inherent issues of collaborative filtering approach such as cold-start, sparsity and compared against static and traditional collaborative systems. The outcomes indicate that the proposed system yields higher values in quality standards and minimizes the drawbacks of the traditional recommender system.