| clear query|facets|time |
Search criteria: RecommenderJob.
Results from 11 to 20 from
547 (0.358s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
...Log-likelihood similarity is a bit of a force-fit of the concept of the LLR. It is basically a binarizing and sparsifying filter applied to cooccurrence counts. As such, it is em...
|
|
|
Author: Ted Dunning,
2013-04-12, 22:03
|
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
...On Wed, Apr 10, 2013 at 10:38 AM, Pat Ferrel wrote: I don't....
|
|
|
Author: Ted Dunning,
2013-04-10, 22:48
|
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
...On Sat, Apr 6, 2013 at 3:26 PM, Pat Ferrel wrote: Well.... rows of B and A should match so columns of B' and rows of A rather than the reverse. Yes. Exactly. ...
|
|
|
Author: Ted Dunning,
2013-04-08, 21:31
|
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
... On Apr 4, 2013, at 5:17 PM, Pat Ferrel wrote: As I mentioned in the other response I sent, only the user id's need to match. Any item whose column in B is all zero cannot be recommended...
|
|
... is probably rare and in any case, we know nothing about it. Any zero row of either A or B will case that user's behavior to be ignored for the purposes of cross recommendation. That is, again...
|
|
|
Author: Ted Dunning,
2013-04-05, 12:54
|
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
...-mind. But you are right about (B'A) A' being historical recommendations for everybody in A. Actually, I think that B'A has rows taken from the b-items and columns taken from the a-items. Each row...
|
|
... of B'A consists of a row of indicators that lead to the recommendation of the item corresponding to that row. This is a very handy form that needn't be further transformed. I don't see why...
|
|
|
Author: Ted Dunning,
2013-04-05, 12:49
|
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
...This may not quite be true because the RSJ is able to take some liberties. The origin of these is that A'A can be viewed as a self join. Thus as rows of A are read, the cooccurre...
|
|
|
Author: Ted Dunning,
2013-04-05, 13:04
|
|
|
Re: cross recommender - Mahout - [mail # user]
|
|
...Sebastian, What about the assumption that the matrix is symmetric? A'A is symmetric, but B'A is not. On Wed, Apr 3, 2013 at 12:08 AM, Sebastian Schelter <[EMAIL PROTECT...
|
|
|
Author: Ted Dunning,
2013-04-03, 06:33
|
|
|
Re: Cross recommendation - Mahout - [mail # user]
|
|
...On Sun, Feb 24, 2013 at 8:39 AM, Pat Ferrel wrote: The cooccurrence oriented item-based recommenders should be fine. I was expecting to train one recommender with (user, item...
|
|
...+action) and call The second recommender is redundant. ...
|
|
|
Author: Ted Dunning,
2013-02-24, 17:12
|
|
|
Re: Cross recommendation - Mahout - [mail # user]
|
|
... form doesn't have a uniform set of users to connect the items together. When you compute the cooccurrence matrix you get A_1' A_1 + A_2' A_2 which gives you recommendations from 1=>1 and from...
|
|
... 2=>2, but no recommendations 1=>2 or 2=>1. Thus, no cross recommendations. On Sat, Feb 23, 2013 at 10:39 AM, Pat Ferrel wrote: ...
|
|
|
Author: Ted Dunning,
2013-02-24, 06:06
|
|
|
Re: Time Based Recommender System - Mahout - [mail # user]
|
|
... gain, look at how the recommendation system feeds itself and how alternative exploration options feed the recommendation system. The question here is how to get the recommendation engine...
|
|
... to explore more when appropriate and less when no. Exploring now (i.e. bringing in more diversity in recommendations) pays off tomorrow because the system gets new kinds of data. Not exploring now...
|
[+ show more]
[- hide]
| ... pays off today because you recommend what you know already works. How to trade these off is a big question. Presumably the things one learns from Bayesian Bandits would be very helpful... |
|
|
Author: Ted Dunning,
2013-05-01, 18:03
|
|
|
|
