You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by Saikat Kanjilal <sx...@hotmail.com> on 2012/02/14 21:32:15 UTC
Idea
Hi Guys,I have been researching the various algorithms in mahout for my usecase and am reading through various papers as well as code, I was wondering if it might be a good idea to have like a chart that outlines each of the algorithms and typical use cases of when one uses that algorithm, this would allow users to quickly get a sample implementation up and running. I would be glad to help with this if folks find this helpful. My use case involves building a set of algorithms that takes in training data surrounding a set of variables each of which contains/contributes a percentage weight and then classifies users into buckets, we can then provide a list of items appropriate for those users based on running item similarity algorithms in that bucket.
Best Regards
Re: Idea
Posted by Lance Norskog <go...@gmail.com>.
Here is a firehose of info for you:
http://www.lucidimagination.com/search/?q=tdunning#%2Fp%3Amahout
On Wed, Feb 15, 2012 at 5:16 AM, Grant Ingersoll <gs...@apache.org> wrote:
> Sounds like a great idea. Wiki would be a great place to put it.
>
>
> On Feb 14, 2012, at 3:32 PM, Saikat Kanjilal wrote:
>
>>
>> Hi Guys,I have been researching the various algorithms in mahout for my usecase and am reading through various papers as well as code, I was wondering if it might be a good idea to have like a chart that outlines each of the algorithms and typical use cases of when one uses that algorithm, this would allow users to quickly get a sample implementation up and running. I would be glad to help with this if folks find this helpful. My use case involves building a set of algorithms that takes in training data surrounding a set of variables each of which contains/contributes a percentage weight and then classifies users into buckets, we can then provide a list of items appropriate for those users based on running item similarity algorithms in that bucket.
>>
>> Best Regards
>
> --------------------------------------------
> Grant Ingersoll
> http://www.lucidimagination.com
>
>
>
--
Lance Norskog
goksron@gmail.com
Re: Idea
Posted by Grant Ingersoll <gs...@apache.org>.
Sounds like a great idea. Wiki would be a great place to put it.
On Feb 14, 2012, at 3:32 PM, Saikat Kanjilal wrote:
>
> Hi Guys,I have been researching the various algorithms in mahout for my usecase and am reading through various papers as well as code, I was wondering if it might be a good idea to have like a chart that outlines each of the algorithms and typical use cases of when one uses that algorithm, this would allow users to quickly get a sample implementation up and running. I would be glad to help with this if folks find this helpful. My use case involves building a set of algorithms that takes in training data surrounding a set of variables each of which contains/contributes a percentage weight and then classifies users into buckets, we can then provide a list of items appropriate for those users based on running item similarity algorithms in that bucket.
>
> Best Regards
--------------------------------------------
Grant Ingersoll
http://www.lucidimagination.com