Recommendations for new users

[Ahmet Ylmaz <ah...@yahoo.com>]

Hi,
We are planning to use Mahout for our movie recommender system. And we are planning to use SVD for model building.

When a new user comes we will require him/her to rate a certain number of movies (say 10).

In order to recommend movies to this new user we have to rebuild the entire model. But this not appealing in terms of computational load.


I'm looking for better solutions.


For FunkSVD, one solution seems to be retraining the model *only* on the new user, in order to learn the factors associated with him.
Since there are not many ratings associated with the new user you can learn the new user's factors in a quite negligible time. 

Actually this solution seems not to be difficult to implement. So, I wonder why this is not implemented in Mahout given that in commercial settings it is very important to be able to immediately recommend items to users after they give some ratings.

Thank you
Ahmet

Re: Recommendations for new users

[Sean Owen <sr...@gmail.com>]

Oops: http://stackoverflow.com/questions/12857693/mahout-how-to-make-recommendations-for-new-users

On Fri, Oct 12, 2012 at 5:03 PM, Eric Link <er...@ericmlink.com> wrote:
> Do you have a link to your stack overflow answer?  Thx. - Eric

Re: Recommendations for new users

[Eric Link <er...@ericmlink.com>]

Do you have a link to your stack overflow answer?  Thx. - Eric


On Oct 12, 2012, at 10:54 AM, Sean Owen <sr...@gmail.com> wrote:

> See my answer on StackOverflow. Yes it is important.
> On Oct 12, 2012 4:23 PM, "Ahmet Ylmaz" <ah...@yahoo.com> wrote:
> 
>> Hi,
>> We are planning to use Mahout for our movie recommender system. And we are
>> planning to use SVD for model building.
>> 
>> When a new user comes we will require him/her to rate a certain number of
>> movies (say 10).
>> 
>> In order to recommend movies to this new user we have to rebuild the
>> entire model. But this not appealing in terms of computational load.
>> 
>> 
>> I'm looking for better solutions.
>> 
>> 
>> For FunkSVD, one solution seems to be retraining the model *only* on the
>> new user, in order to learn the factors associated with him.
>> Since there are not many ratings associated with the new user you can
>> learn the new user's factors in a quite negligible time.
>> 
>> Actually this solution seems not to be difficult to implement. So, I
>> wonder why this is not implemented in Mahout given that in commercial
>> settings it is very important to be able to immediately recommend items to
>> users after they give some ratings.
>> 
>> Thank you
>> Ahmet

Re: Recommendations for new users

[Sean Owen <sr...@gmail.com>]

See my answer on StackOverflow. Yes it is important.
On Oct 12, 2012 4:23 PM, "Ahmet Ylmaz" <ah...@yahoo.com> wrote:

> Hi,
> We are planning to use Mahout for our movie recommender system. And we are
> planning to use SVD for model building.
>
> When a new user comes we will require him/her to rate a certain number of
> movies (say 10).
>
> In order to recommend movies to this new user we have to rebuild the
> entire model. But this not appealing in terms of computational load.
>
>
> I'm looking for better solutions.
>
>
> For FunkSVD, one solution seems to be retraining the model *only* on the
> new user, in order to learn the factors associated with him.
> Since there are not many ratings associated with the new user you can
> learn the new user's factors in a quite negligible time.
>
> Actually this solution seems not to be difficult to implement. So, I
> wonder why this is not implemented in Mahout given that in commercial
> settings it is very important to be able to immediately recommend items to
> users after they give some ratings.
>
> Thank you
> Ahmet