| clear query|facets|time |
Search criteria: RecommenderJob.
Results from 41 to 50 from
557 (0.572s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: recommendations - Mahout - [mail # user]
|
|
... search-term. Depending on what kind of recommendation system you are using, the actual mechanics will be different, but the shape of the computation will still be fairly similar to the matrix...
|
|
|
Author: Ted Dunning,
2010-08-30, 16:44
|
|
|
Re: Top-N recommendations from SVD - Mahout - [mail # user]
|
|
...I would recommend against a mutable object on maintenance grounds. Better is to keep the threshold that a new score must meet and only construct the object on need. That cuts...
|
|
|
Author: Ted Dunning,
2013-03-06, 16:01
|
|
|
Re: Top-N recommendations from SVD - Mahout - [mail # user]
|
|
...Hmm... each users recommendations seems to be about 2.8 x 20M Flops = 60M Flops. You should get about a Gflop per core in Java so this should about 60 ms. You can make this faster...
|
|
... with more cores or by using ATLAS. Are you expecting 3 million unique people every 80 hours? If no, then it is probably more efficient to compute the recommendations on the fly. How many...
|
[+ show more]
[- hide]
| ... recommendations per second are you expecting? If you have 1 million uniques per day (just for grins) and we assume 20,000 s/day to allow for peak loading, you have to do 50 queries per second peak... |
| .... This is quite plausible with bad arrangement of the inner loops. I think that you would have highest performance computing the recommendations for a few thousand items by a few thousand users at a time... |
|
|
Author: Ted Dunning,
2013-03-06, 03:47
|
|
|
Re: Top-N recommendations from SVD - Mahout - [mail # user]
|
|
...That sounds way too long. How is the U matrix stored? What type? On Wed, Mar 6, 2013 at 6:44 AM, Josh Devins wrote: ...
|
|
|
Author: Ted Dunning,
2013-03-06, 16:02
|
|
|
Re: Top-N recommendations from SVD - Mahout - [mail # user]
|
|
...Well, it would definitely not be the for time I counted incorrectly. Anytime I do arithmetic the result should be considered suspect. I do think my numbers are correct, but then ...
|
|
|
Author: Ted Dunning,
2013-03-06, 10:13
|
|
|
Re: How to interpret recommendation strength - Mahout - [mail # user]
|
|
... then weight the item item matrix according to the frequency of the remaining non-zero elements in it. I often recommend achieving this end by simply creating a document per row of the item item...
|
|
|
Author: Ted Dunning,
2012-11-16, 05:27
|
|
|
Re: How to interpret recommendation strength - Mahout - [mail # user]
|
|
...My own preference (pun intended) is to use log-likelihood score for determining which similarities are non-zero and then use simple frequency weighting such as IDF for weighting the similari...
|
|
|
Author: Ted Dunning,
2012-11-15, 18:47
|
|
|
Re: Number of Clustering MR-Jobs - Mahout - [mail # user]
|
|
...This is a longstanding Hadoop issue. Your suggestion is interesting, but only a few cases would benefit. The problem is that splitting involves reading from a very small number o...
|
|
|
Author: Ted Dunning,
2013-03-28, 09:20
|
|
|
Re: Number of Clustering MR-Jobs - Mahout - [mail # user]
|
|
...Your idea that this is related to your single input file is the most likely cause. If your input file is relatively small then splitting it up to force multiple mappers is the easiest ...
|
|
|
Author: Ted Dunning,
2013-03-28, 00:26
|
|
|
Re: Number of Clustering MR-Jobs - Mahout - [mail # user]
|
|
...Do you mean that it starts a single map task? On Wed, Mar 27, 2013 at 5:10 PM, Sebastian Briesemeister wrote: ...
|
|
|
Author: Ted Dunning,
2013-03-27, 17:06
|
|
|
|
