Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Threaded View
MapReduce, mail # user - product recommendations engine


Copy link to this message
-
Re: product recommendations engine
Sofia Georgiakaki 2013-02-19, 09:09
Good morning,

Myrrix provides a Recommender that implements a specific recommendation algorithm based on matrix factorization, which is generally efficient in most cases. However, depending on your data and access pattern, it may be better to use Mahout as well, as it provides many different Recommenders. So you can evaluate each implementation and use the recommender that the given time best suits your dataset.

Regards,
Sofia

>________________________________
> From: Manoj Babu <[EMAIL PROTECTED]>
>To: [EMAIL PROTECTED]
>Sent: Tuesday, February 19, 2013 7:03 AM
>Subject: Re: product recommendations engine
>
>
>Hi Sofia,
>
>I am just hearing about the Myrrix project looks interesting. Thanks for sharing the information.
>
>
>Cheers!
>Manoj.
>
>
>On Tue, Feb 19, 2013 at 12:45 AM, Douglass Davis <[EMAIL PROTECTED]> wrote:
>
>Ok thanks.  Myrrix looks like it has much of the set-up work done so I am taking a closer look at that.
>>
>>
>>
>>
>>On Mon, Feb 18, 2013 at 4:00 AM, Sofia Georgiakaki <[EMAIL PROTECTED]> wrote:
>>
>>Hello Douglass,
>>>
>>>you could take a look at Mahout and Myrrix projects. These are two projects thatprovide implementations of recommendation & machine learning algorithms. There are MapReduce implementations as well, to support massive datasets.
>>>In addition, these systems provide client APIs/various integration points, so its easy to integrate them to your system.
>>>
>>>Regards,
>>>Sofia
>>>
>>>
>>>
>>>
>>>
>>>
>>>>________________________________
>>>> From: Douglass Davis <[EMAIL PROTECTED]>
>>>>To: [EMAIL PROTECTED]
>>>>Sent: Monday, February 18, 2013 1:21 AM
>>>>Subject: product recommendations engine
>>>>
>>>>
>>>>
>>>>Hello,
>>>>
>>>>I don't have any prior experience with Hadoop.  I am also not a statistics expert.  I am a software engineer, however, after looking at the docs, Hadoop still seems pretty intimidating to set up. 
>>>>
>>>>I am interested in doing product recommendations.  However, I want to store many things about user behavior, for example whether they click on a link in an email, how they rate a product, whether they buy it, etc.  Then I would like to come up with similar items that a user may like.  I have seen an example just based on user ratings, but would like to add much more data.
>>>>
>>>>Also, I think the clustering could be used in terms of recommending based on similar descriptions, attributes, and keywords.
>>>>
>>>>Or, I could use a combination of the two approaches.
>>>>
>>>>Another question, I wonder if Hadoop takes into account the passage of time.  For example, a user may rate something high, then change their rating a couple months later.
>>>>
>>>>Lastly, my site is based on PHP.  I need to be able to integrate that with Hadoop.
>>>>
>>>>How feasible is this approach?  I saw a clustering example, and a recommendation example based on user ratings.  Are there any other advice, docs, or examples that you could point me to that deals with any of these issues?
>>>>
>>>>Thanks,
>>>>Doug
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>
>
>
>