| clear query|facets|time |
Search criteria: .
Results from 91 to 100 from
2731 (0.647s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: Mathematical background of ALS recommenders - Mahout - [mail # user]
|
|
...Points from across several e-mails -- The initial item-feature matrix can be just random unit vectors too. I have slightly better results with that. You are finding the least-squ...
|
|
|
Author: Sean Owen,
2013-03-25, 10:46
|
|
|
Re: postgres recommendation adapter - Mahout - [mail # user]
|
|
...I think you'd have to define "not working" first On Mon, Mar 25, 2013 at 1:32 AM, Matt Mitchell wrote:...
|
|
|
Author: Sean Owen,
2013-03-25, 10:21
|
|
|
Re: sql data model w/where clause - Mahout - [mail # user]
|
|
...Modify the existing code to change the SQL -- it's just a matter of copying a class that only specifies SQL and making new SQL statements. I think there's a version that even reads from a Pr...
|
|
|
Author: Sean Owen,
2013-03-25, 10:17
|
|
|
Re: ALS-WR on Million Song dataset - Mahout - [mail # user]
|
|
...This highlights the 'cheating' going on here to make this run so fast, and I completely endorse it. The join proceeds by side-loading half of the join into memory. This creates a new possibl...
|
|
|
Author: Sean Owen,
2013-03-20, 10:52
|
|
|
Re: Boosting User-Based with the user's attributes - Mahout - [mail # user]
|
|
...Write a new implementation of UserSimilarity that internally calls 2 other similarity metrics with the same arguments when asked for a similarity. Return their product. On Tue, Mar 19...
|
|
|
Author: Sean Owen,
2013-03-19, 11:02
|
|
|
Re: Boosting User-Based with the user's attributes - Mahout - [mail # user]
|
|
...I'm not sure what you mean. The only thing I am suggesting to combine are two similarity metrics, not data or recommendations. You combine metrics by multiplying their values. On Mon,...
|
|
|
Author: Sean Owen,
2013-03-18, 20:49
|
|
|
Re: ALS-WR on Million Song dataset - Mahout - [mail # user]
|
|
...Yes that's fine input then. Large alpha should go with small R values, not large R. Really alpha controls how much observed input (R != 0) is weighted towards 1 versus how much unobser...
|
|
|
Author: Sean Owen,
2013-03-18, 20:43
|
|
|
Re: ALS-WR on Million Song dataset - Mahout - [mail # user]
|
|
...One word of caution, is that there are at least two papers on ALS and they define lambda differently. I think you are talking about "Collaborative Filtering for Implicit Feedback Datasets". ...
|
|
|
Author: Sean Owen,
2013-03-18, 16:47
|
|
|
Re: Boosting User-Based with the user's attributes - Mahout - [mail # user]
|
|
...There is a difference between the recommender and the similarity metric it uses. My suggestion was to either use your item data with the recommender and hobby data with the similarity metric...
|
|
|
Author: Sean Owen,
2013-03-18, 13:54
|
|
|
Re: Boosting User-Based with the user's attributes - Mahout - [mail # user]
|
|
...You would have to make up the similarity metric separately since it depends entirely on how you want to define it. The part of the book you are talking about concerns rescoring, which is not...
|
|
|
Author: Sean Owen,
2013-03-18, 13:23
|
|
|
|
