, brand, site, price, etc...
- user information, for example which users saved this product
- CTR data from interaction of users with products on our site.
We want to build a recommendation system on top of this data. We are
considering using Solr or Mahout (on EMR) to implement this system.
If this
oduct
recommendation system and one idea is to use solr's MLT functionality.
For each customer I have a list of items they've bought, and I want
to find
similar items that are new to the site.
The problem is that MLT operates on each result found (if I send it
an id,
it will return a list fo
R
id:3)&mlt.fl=mlt-field&mlt.mintf=1" just works fine.
Cheers
Avlesh
On Fri, Jul 31, 2009 at 5:38 PM, Andrew Ingram wrote:
> Hi all,
> I'm trying various methods of building a user-specific product
> recommendation system and one idea is to use solr's MLT functionalit
e:
> Hi all,
> I'm trying various methods of building a user-specific product
> recommendation system and one idea is to use solr's MLT functionality.
>
> For each customer I have a list of items they've bought, and I want to find
> similar items that are new to the
Hi all,
I'm trying various methods of building a user-specific product
recommendation system and one idea is to use solr's MLT functionality.
For each customer I have a list of items they've bought, and I want to find
similar items that are new to the site.
The problem is that
