ICFR: An effective incremental collaborative filtering based recommendation architecture for personalized websites

To solve the problem that users' retrieval intentions are seldom considered by personalized websites, we propose an improved incremental collaborative filtering (CF)-based recommendation implementation method (ICFR) in this paper. The ICFR model uses one of the most popular recommendation algorithms - the collaborative filtering recommendation algorithm - for personalized websites. This paper first uses a CF algorithm to obtain the relationship between user preferences and recommended content. Second, the browsing behaviour information of users is extracted by analysing Web logs and is then converted into ratings. Finally, an incremental algorithm is designed to update historical user preference data. Based on this established model, we propose some cases for this architecture, which illustrate that the ICFR model is suitable for personalized website recommendations.