Community Spring Cleaning week is here! Join your fellow Maveryx in digging through your old posts and marking comments on them as solved. Learn more here!

Alteryx Designer Desktop Discussions

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

Linear regression for multiple objects in one column.

nidah5
8 - Asteroid

The data has customer level data. and  want to check the linear regression of each customer revenue to their complaints. The linear regression column is where want to calculate regression for each customer. a single model for all

CUSTOMERREVENUECOMPLAINTSLINEAR REGRESSION
ACSC299286797.97888751720 
ABB6873611.031129461229 
AVT231346386.65415810892 
18 REPLIES 18
grazitti_sapna
17 - Castor

@nidah5 , you can try to re-install the predictive tool.

Please refer to this link - https://help.alteryx.com/current/designer/download-and-use-predictive-tools

 

If it still doesn't help I will suggest you to talk with the support at support@alteryx.com

 

I hope it helps.

 

Thanks.

Sapna Gupta
nidah5
8 - Asteroid

thanks a lot for helping.

i have run the model.

i can see the correlation is showed for the whole model.

is there any way to be shown by accounts.

 

my main purpose is to check the linearity of revenue and complaints for each account.

nidah5
8 - Asteroid

@grazitti_sapna

i have attached the full workflow, where the goal is to find the correlation using pearson method for the revenue and the complaints for all customers. i have used the lag value for complaints as want to check if complaint has been raised 3 months back is there any effect on revenue. the result shows for max customers the Correlation is less than 0.7 which indicates revenue goes down and now would further ant to check if there is linearity between revenue and complaints using linear regression.

 

can you validate the workflow according to the problem statement

grazitti_sapna
17 - Castor

Hi @nidah5 

 

Sorry for reverting you late . Actually I just saw the workflow and find out that the validation dataset that you provided doesn't contain any customer name from training dataset as a result not able to validate on the same. Could you please check once or shall I create sample from the initial dataset?

Sapna Gupta
nidah5
8 - Asteroid

Can you please share the sample dataset?

grazitti_sapna
17 - Castor

Hi @nidah5 

 

The sample dataset is the text input in the Alteryx workflow. Please find the attached file.

Sapna Gupta
nidah5
8 - Asteroid

Hi,

This is the LR result from the old dataset. my question would be does T value signifies the relation of revenue and complaints for each customer? if yes then that's what i am exactly looking for, if not then what is the correct way to find it?

nidah5_0-1603776325402.pngnidah5_1-1603776360189.png

 

grazitti_sapna
17 - Castor

Hi @nidah5 

 

Pr(>|t|) value signifies the relationship between predictor and response not the t value. As we can see that for each customer there is relation between predictor and response. If it helps you in anyway to what you are looking for then please accept the solution.

Sapna Gupta
nidah5
8 - Asteroid

@grazitti_sapna  Yes, it surely does. thanks a lot, you have been really helpful.

Labels