Personalization portal system based on collaborative filtering algorithm

Existing collaborative filtering algorithms do not consider the change of user interests. For this reason, the systems may recommend unsatisfactory items when user´s interest has changed. To solve this problem, by analysising and collecting user´s information and behavior, proposed and established “user-page” matrix as a collaborative filtering algorithm interest matrix, and take the initiative to recommend relevant content to users. The improved algorithm has obviously improved on recommendation accuracy. The personalization portal system based on this has good effect in the fact.