On Mon, Jul 16, 2012 at 9:33 AM, Cleophus Pereira <cleophus.pere...@mphasis.com> wrote: > You mentioned to use IDRescorer to get data based on user preferences. But > in mahout schema we have just itemid (number) and scores(double). How can we > determine purely based on this what is user preference.
I don't know what you mean -- there is no user preference involved here. You are considering recommending item A to user B because it has estimated pref value X. B has no existing pref for A or else it would not be a candidate! > I have implemented class IDRescorer and overrided to method - isFiltered and > rescorer which return results based on rating value(double). > > In such case do I need to get preference details for each ItemID and put > validation in isFiltered. This will cause overhead while running everytime. > As I need to get user preferences and match with preference details for each > item id. > Is this the way you recommend? If my understanding is right will not it > affect the performance? You can do whatever you want in this method -- there is no *need* about it. I can't think of a realistic use case that needs looking up a pref.
