N-screen aware Multicriteria Hybrid Recommender system using weight based subspace clustering

In this paper, we propose a recommender system for N-screen services in which users have multiple devices with different capabilities. In N-screen services, a user can use various devices in different locations and times, and can change devices while the service is running. We provide N-screen aware recommendations by considering the user N-screen device attributes such as screen resolution, media codec, CPU, remaining battery, and access network, etc, and the user temporal usage pattern information that have not been considered in existing systems. We introduce a user device profile collaboration agent, manager and N-screen control server for N-screen aware recommendation support. Furthermore, we also propose a multi-criteria hybrid framework that incorporates the user preferences, demographic and N-Screen device information. In addition, we suggest an individual feature & subspace weight based clustering (IFSWC) to assign different weights to each subspace and each feature within a subspace in the hybrid framework. We also improve the accuracy, precision, scalability, sparsity and cold start issues. The experimental results demonstrate the effectiveness and prove the aforementioned statements.