My guess is that at these volumes, you may well be wanting to use a more generic co-occurrence count based solution for the off-line portion. You should be good experimenting with Taste since a larger scale analysis can likely be retrofitted in a compatible way.
On Thu, Jul 23, 2009 at 4:09 PM, Aurora Skarra-Gallagher < [email protected]> wrote: > We are looking at starting with 70M users and scaling up to 500M > eventually. It is hard for me to estimate the number of items. We could be > starting out with 100, but as these items are entities that we extract, > there could be tens of thousands eventually. I would guess that most users > would have less than 100 of these. > -- Ted Dunning, CTO DeepDyve
