Subject: Re: Hybrid RecSys — ways to do it


When stacking recommenders, you need to have features that represent:

a) the output of the recommenders in question

b) features that you think will help.  Number of data points is a
classic.  Log transformations are often a good idea with count
features.

c) interactions of (a) and (b) are generally critical

If you have a per-user quality or satisfaction indicator and a
per-user current model indicator then you might be able to use these
as a feature for an interesting "if it ain't broke, don't fix it"
stacking model.

On Thu, Jun 9, 2011 at 3:51 PM, Marko Ciric <[EMAIL PROTECTED]> wrote: