Abstract: A method of collaborative filtering recommendations using implicit user actions is provided herein. The method includes the following steps: collecting user preference of content items from the crowd; generating for each real content item, a shadow content item; updating preference for the shadow items based on the user preference of corresponding real content items; feeding a collaborative recommendation engine a list of content items and their corresponding preferences, wherein the list comprises both real and shadow content items; and filtering out the shadow content items from an output of the recommendation engine, to yield a list of recommended real content items.

Abstract: A method of sorting search results by recommendation engine is provided herein. The method starts off with receiving a search query from a user associated with a specific user ID. The method goes on to applying the search query to a search engine and to a content database, to yield search results. The method then goes on to retrieving a profile of the specific user from a preferences and history database, based on the user ID. Then the method proceeds to reordering the search results by a recommendation engine, based on the retrieved profile. Finally, the method concludes with providing the user with the reordered search results such that the order matches the profile of the user.