According to another embodiment of the invention, an approach is provided for estimating how a user would rate an item that the user has not yet rated. The approach is applicable to any type of items, including rental items such as movies and games, and the invention is not limited to any particular type of item. The approach is applicable to a wide variety of contexts and is ideally suited for automatically selecting rental items to be recommended for rental. One or more items that have been rated by the user are identified. Then, one or more other users are identified that have rated the one or more items and given ratings to the one or more items that are substantially similar to ratings given by user to the one or more items. Finally, an estimation is made how the user would rate the item that the user has not yet rated based upon how the one or more other users rated the item.