mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Emilio Suarez <Emilio.Sua...@intela.com>
Subject Re: Recommender with ratings takes a long time to process
Date Fri, 11 May 2012 20:52:18 GMT
Great!,  trying that now… thanks again Sean!

-emilio
On May 11, 2012, at 11:50 AM, Sean Owen wrote:

Yes, you want the sampling one so you can reduce the number of
neighbors you consider.

On Fri, May 11, 2012 at 6:47 PM, Emilio Suarez <Emilio.Suarez@intela.com<mailto:Emilio.Suarez@intela.com>>
wrote:
Thanks Sean,

So, do you suggest something like this?

       LogLikelihoodSimilarity similarity = new LogLikelihoodSimilarity(fileDataModel);
       PreferredItemsNeighborhoodCandidateItemsStrategy candidateStrategy = new PreferredItemsNeighborhoodCandidateItemsStrategy();
       recommender = new GenericItemBasedRecommender(fileDataModel, similarity, candidateStrategy,
candidateStrategy);

or this?

       LogLikelihoodSimilarity similarity = new LogLikelihoodSimilarity(fileDataModel);
       SamplingCandidateItemsStrategy candidateStrategy = new SamplingCandidateItemsStrategy();
       recommender = new GenericItemBasedRecommender(fileDataModel, similarity, candidateStrategy,
candidateStrategy);


-emilio

You need to apply a CandidateItemStrategy to reduce the number of
elements you consider, or else it will take a very long time because
almost the entire model is a candidate for recommendation.



Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message