Perhaps wrongly, but RecommenderJob has been a gateway to Mahout for my colleagues and I. It is easy to use, and intuitive. We are currently using it for an early stage of buying gap analysis. The fact that it would not recommend items with an expressed prior preference was key to considering the algorithm, as having to filter the recommendations would have made it far less of a turnkey approach, right now.
If our experience is indicative of a future, wider interest, I think this is an important usability feature. Many thanks, I'll report the issue, when I figure out where. :) Rafal -- Rafal Lukawiecki Pardon my brevity, sent from a telephone. On 31 Jul 2013, at 23:45, "Ted Dunning" <[email protected]> wrote: > On Wed, Jul 31, 2013 at 3:20 PM, Sebastian Schelter <[email protected]> wrote: > >> That's true in general, but for usecases such as generating recommendations >> in batch for personalized newsletters, its a nice to have feature. >> >> I also have the impression that most users expect to not see items with >> interactions. Ideally we would have a flag that lets users choose which >> behavior they want. >> >> I think one of the big benefits of ItemSimilarityJob and RecommenderJob is >> that these are "CSV file in" and "CSV file out" jobs that are super easy to >> use and we should keep that up. > > Fair comment. But I think that business logic can't be ignored. > > Dithering, anti-flood, blackout dates and many other factors all have to be > applied outside the recommendation engine. Once you go there, one more > consideration makes little difference it seems. > > On the other hand, one less should not matter either!
