Efficient Data Update for Location-Based Recommendation Systems

Location-based recommendation systems are obtaining interests from the business and research communities. However, the efficiency of the update on the recommendation models is one of the most important issues. In this paper, we propose an efficient approach to update a recommendation model, User-centered collaborative location and activity filtering (UCLAF). The computational complexity of the model building is analyzed in details. Subsequently, our approach to update the models only the necessary parts is presented. As a result, the recommendation models obtained from our approach is exactly the same as the traditional re-calculation approach. The experiments have been conducted to evaluate our proposed approach. From the results, it is found that our proposed approach is highly efficient.