LAUSR

Movie recommendation is an important activity in the people's daily entertainment. Typically, through analysing the users' ever-watched movie list, a movie recommender system can recommend appropriate new movies to the target user. However, traditional movie recommendation techniques, e.g., collaborative filtering (CF) often face the following two challenges. First, as CF is essentially a traversal technique, the recommendation efficiency is often low. Second, traditional movie recommender systems often assume that the users' ever-watched movie list for decision-making is centralised, which makes it hard to be applied to the distributed movie recommendation scenarios. In view of these challenges, in this paper, we bring forth an efficient and privacy-aware online movie recommendation approach based on hashing technique. Through experiments on famous MovieLens dataset, we show that our proposal shows a better performance compared with other approaches in terms of recommendation efficiency and accuracy while users' private information is protected.