You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@mahout.apache.org by Ayad Al-Qershi <al...@gmail.com> on 2012/03/08 10:52:46 UTC
why log-likelihood similarity is faster than Tanimoto coefficient
Dear All,
can anyone tell me why running the recommender job with log-likelihood
similarity performs better (faster) than Tanimoto on the same dataset ?
Thank you,
Iyad
Re: why log-likelihood similarity is faster than Tanimoto coefficient
Posted by Sean Owen <sr...@gmail.com>.
I don't expect they are different in speed. Both do about exactly the
same thing and finish with a simple computation.
On Thu, Mar 8, 2012 at 9:52 AM, Ayad Al-Qershi <al...@gmail.com> wrote:
> Dear All,
>
> can anyone tell me why running the recommender job with log-likelihood
> similarity performs better (faster) than Tanimoto on the same dataset ?
>
> Thank you,
>
> Iyad
Re: why log-likelihood similarity is faster than Tanimoto coefficient
Posted by manish dunani <ma...@gmail.com>.
I was also noted loglikelihood is little bit faster than tanimoto .In the
sense it do not compute any preferences.so,that's why i feel the same.
>
>
--
MANISH DUNANI
-THANX
Re: why log-likelihood similarity is faster than Tanimoto coefficient
Posted by Sebastian Schelter <ss...@googlemail.com>.
Ayad,
we need a little more details. How much faster is it, how does your data
look like? Where do you run the algorithm?
Can you provide us with the output of the jobs?
--sebastian
On 08.03.2012 10:52, Ayad Al-Qershi wrote:
> Dear All,
>
> can anyone tell me why running the recommender job with log-likelihood
> similarity performs better (faster) than Tanimoto on the same dataset ?
>
> Thank you,
>
> Iyad
>