The downsampling should have a target size after sampling so that users with that many or fewer ratings are not down-sampled at all.
This is easy to do using reservoir sampling or anything similar. You can also just keep the first or most recent ratings. Or you can use a sampler biased toward either of those extremes. On Mon, Dec 5, 2011 at 12:20 AM, Daniel Zohar <disso...@gmail.com> wrote: > Another issue to take into account, is to try and not down-sample too much > so users with 1-2 preferences still get decent results. >
