Hello everyone! I am a student learning Alteryx - beginner level. I tried to build this basic model but the data stops flowing at a certain point. I am very lost, I don't fully understand what I have done despite searching and reading available resources. Please help.
Also, please let me know if someone is keen to be an Alteryx personal tutor. If you can share how to learn Alteryx most effectively for building marketing-related models, it would be much appreciated! Thank you in advance 🙏
Solved! Go to Solution.
Check your error log when you run it and click on the tool name to navigate to the error! In this case, you are missing a connection to your Join tool
Hello, thank you for your reply. There were originally 2 inputs (from the Union tool and from the Formula tool that calculates response rate). However, I have been adjusting so many connections and other things but there appear to be too many null values and both predictive tools showed that there is no input. Apparently, something is wrong since the feature engineering part. Please help 🙏
I can't help without a complete workflow...and I don't know what you are trying to accomplish so I can't help further without more information
You have zero records going into your predictive tools... you need to have data going into it, but your Join makes it zero. So everything after will error!
@Jenny_Vu
I am not good at Predictive tools either but I followed this starter kit and gave a try.
I would recommend to throughly study the sample in the Starter Kit then make clear what is the Goal that you want to predict and what would be the possible variables that may cause impact on the predictive goal.
https://community.alteryx.com/t5/Community-Gallery/Predictive-Analytics-Starter-Kit/tac-p/1390088#M2...
Thank you very much for your help!
Thank you very much for your help, Qiu!
I second Qiu's response about learning the methods in Alteryx.
In this case, it's the union that is incorrect. You have a set of 529 records. Where you have that union, what you want to do is have the original dataset, with [Sum_Sales] attached, and the other generated fields attached, which requires a Join, not a Union. It can be either a "Join Multiple", or a couple of normal Join tools, then your next join, adds on the stats per Household Type.
The reason that I second trying one of the starter kits, is that if you don't understand the method going into a predictive model, why should anyone believe the prediction coming out the other side. You had 1587 records going into the predictive model, with many many Nulls, as the union was just stacking the outputs... and Nulls are kryptonite to Predictive models. Even if you could have got that to work with the nulls, most of the data was duplicated but not attached to the target, and so there would not have been any meaningful result.