| clear query|facets|time |
Search criteria: RecommenderJob.
Results from 21 to 30 from
555 (0.325s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: Cross recommendation - Mahout - [mail # user]
|
|
...On Fri, Feb 22, 2013 at 9:48 AM, Pat Ferrel wrote: Add the scores. With coherent weighting schemes that should work just fine. To do this, get the two recommendation lists and add...
|
|
|
Author: Ted Dunning,
2013-02-22, 18:42
|
|
|
Re: Cross recommendation - Mahout - [mail # user]
|
|
..._p will produce view-based cross This term only produces purchase recommendations. If you want both, you need to include the A'A h_v + A'B h_p part of the vector. Yes. Yes. In pig, there is a co...
|
|
|
Author: Ted Dunning,
2013-02-22, 05:41
|
|
|
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
|
|
|
Re: Recommendation based on the attributes - Mahout - [mail # user]
|
|
...Yes. Recommend the attributes and then do a search for items with those attributes. You can also combine the final retrieval with a normal retrieval. On Tue, Feb 19, 2013 at 9:53 PM...
|
|
|
Author: Ted Dunning,
2013-02-20, 07:02
|
|
|
Re: Time Based Recommender System - Mahout - [mail # user]
|
|
... doesn't change. Likewise for an item. If you use implicit feedback and recommend based on recent behavior most of the practical benefit to modeling the time dynamics goes away since you aren...
|
|
|
Author: Ted Dunning,
2013-04-30, 15:46
|
|
|
Re: Mathematical background of ALS recommenders - Mahout - [mail # user]
|
|
...No. We don't. We used to use Lanczos, but that has improved. On Mon, Mar 25, 2013 at 4:43 PM, Abhijith CHandraprabhu <[EMAIL PROTECTED] ...
|
|
|
Author: Ted Dunning,
2013-03-25, 16:36
|
|
|
Re: Mathematical background of ALS recommenders - Mahout - [mail # user]
|
|
...Yes. But SSVD != Lanczos. Lanczos is vector at at time sequential like you said. SSVD does all the vectors in one go. That one go requires a few steps, but does not r...
|
|
|
Author: Ted Dunning,
2013-03-25, 15:25
|
|
|
Re: Mathematical background of ALS recommenders - Mahout - [mail # user]
|
|
...Well, actually, you can. LSI does exactly that. What the effect is of doing this is not clear to me. Do you know what happens if you assume missing values are 0? On M...
|
|
|
Author: Ted Dunning,
2013-03-25, 11:14
|
|
|
Re: Mathematical background of ALS recommenders - Mahout - [mail # user]
|
|
...Even more in-line. On Mon, Mar 25, 2013 at 11:46 AM, Sean Owen wrote: Possibly. Or not. The stochastic project method gives you an SVD pretty quic...
|
|
|
Author: Ted Dunning,
2013-03-25, 11:06
|
|
|
Re: Mathematical background of ALS recommenders - Mahout - [mail # user]
|
|
...If you have an observation matrix that actually is low rank and you start with the exact value of U, then one iteration on M will suffice to solve the system. Likewise, if you have M, ...
|
|
|
Author: Ted Dunning,
2013-03-25, 05:47
|
|
|
|
