Time-aware distributed service recommendation with privacy-preservation

As a promising way to extract insightful information from massive data, service recommendation has gained ever-increasing attentions in both academic and industrial areas. Recently, the Locality-Sensitive Hashing (LSH) technique is introduced into service recommendation to pursue high recommendation efficiency and the capability of privacy-preservation, especially when the historical service quality (QoS) data used to make recommendation decisions are distributed across different platforms. However, existing LSH-based service recommendation approaches often face the following challenge: they often assume that the QoS data for service recommendation are static and unique, without considering the influence of dynamic context (e.g., time) on QoS. In view of this challenge, we extend the traditional LSH technique to incorporate the time factor and further propose a novel time-aware and privacy-preserving service recommendation approach based on LSH. Finally, we conduct extensive experiments on a large-scale real-world dataset, i.e., WS-DREAM, to validate the effectiveness and efficiency of our proposal. The experiment results show that our approach achieves a good tradeoff between recommendation accuracy and efficiency while guaranteeing privacy-preservation.