A Temporal-Aware Hybrid Collaborative Recommendation Method for Cloud Service

With the rapid development of cloud computing, large scale of cloud services are provided to users. Recommender systems have been proven to be valuable tools to deal with information overload and be able to provide appropriate recommendations to users. The cloud environment is dynamic and uncertain, which makes the quality of cloud services time-sensitive. However, most existing recommender systems did not take temporal influence into consideration, therefore could not accommodate the dynamic cloud environment. In view of this challenge, we propose a temporal-aware hybrid collaborative recommendation method for cloud service. It aims at providing users with appropriate recommendations from time-sensitive cloud services. In our method, by distinguishing temporal QoS metrics from stable QoS metrics, temporal influence is integrated into classical neighborhood-based collaborative recommender algorithm. Besides, to get an optimal recommendation, a temporal-aware latent factor model based on tensor decomposition is proposed and combined to improve the recommendation performance. Finally, experiments are designed and conducted to demonstrate the efficiency of our method.