I see. If you're not using collaborative filtering then you're not using Recommender / DataModel. So I don't think your solution includes adding these users / items to the model. Yes, you can start by recommending a simple global top-N most popular items, or, do something reasonable based on whatever you know about the user.
On Wed, Jul 11, 2012 at 5:44 PM, Jaspreet Singh <[email protected]> wrote: > Thanks for your reply Sean. The objective is to solve the cold start > problem, through something other than collaborative filtering. I am looking > to add extra functionality to use in case an item is not currently in use > and use it to compare these items to existing items in use. Than these > could be offered to users using other similar items. > > Regards, > Jaspreet
