Join the Alteryx Community’s Maveryx Summer Cup event! Compete, network with others, and earn your gold through a series of challenges from July 24th to August 11th. Learn more about the event here.

Alteryx Designer Desktop Discussions

Find answers, ask questions, and share expertise about Alteryx Designer Desktop and Intelligence Suite.

difference between Cross-validation present in Boosted model and stand alone function

sriharimech
6 - Meteoroid

Hi All,

 

I see cross validation in Boosted model and Linear regression customization. what difference does it make if I use cross validation from the predictive tool.

 

I used cross validation present in predictie for boosted model and get below error please help. 

 

sriharimech_0-1608389852329.png

This is my configuration in booste model when I used standalone cross validaiton 

 

sriharimech_1-1608389896177.png

 

2 REPLIES 2
joshuaburkhow
ACE Emeritus
ACE Emeritus

Hey @sriharimech 

 

It actually looks like you are not using cross-validation in your boosted model. You have out-of-the-bag selected. You can read more about the options here https://help.alteryx.com/current/designer/boosted-model-tool and I highly recommend reading more on boosted model Tool Mastery https://community.alteryx.com/t5/Alteryx-Designer-Knowledge-Base/Tool-Mastery-Boosted-Model/ta-p/419... 

 

This is also great for cross-fold validation: 

https://community.alteryx.com/t5/Alteryx-Designer-Knowledge-Base/Guide-to-Cross-Validation/ta-p/1179...

 

Joshua Burkhow - Alteryx Ace | Global Alteryx Architect @PwC | Blogger @ AlterTricks
sriharimech
6 - Meteoroid

Thanks. 

 

I did not use cross validation in boosted model as I want to get a neat graph between predicted and actual value using the cross validation tool presnet in predictive. My question is why does cross validaiton works for Linear Regression and Neural network but fails for Boosted Model ?

 

 

Labels