You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@mahout.apache.org by "Nowal, Akshay" <Ak...@SYNTELINC.COM> on 2012/04/11 08:12:27 UTC

How to use Random forest in Mahout

Hi,

 

I am at a beginner level in using Mahout and m planning to build a random forest model on Customer data  to classify churners and non-churners.

Any help on as to how can we go about it in Mahout?

Does any parallelized algorithm for Random forest is available?

Will Naïve Bayes/Complementary Naïve Bayes work in this situation?

 

 

Thanks,

Akshay Nowal

 


RE: How to use Random forest in Mahout

Posted by Ta...@emc.com.
Mahout Random Forest does not seems scale out well. See a recently PAKDD paper on some new implementation based on hadoop:
" Scalable Random Forests for Massive Data.pdf "
 
--Tao

-----Original Message-----
From: Nowal, Akshay [mailto:Akshay_Nowal@SYNTELINC.COM] 
Sent: 2012年4月11日 14:12
To: user@mahout.apache.org
Subject: How to use Random forest in Mahout

Hi,

 

I am at a beginner level in using Mahout and m planning to build a random forest model on Customer data  to classify churners and non-churners.

Any help on as to how can we go about it in Mahout?

Does any parallelized algorithm for Random forest is available?

Will Naïve Bayes/Complementary Naïve Bayes work in this situation?

 

 

Thanks,

Akshay Nowal