how do you split the data set into training, test and validation? After the split what do you do next?

I can spilt it into training and test but how do you do validation? I want to generalise the data decision tree data to prevent overfitting. What do do with these sets after specifically on knime?

You are asking a lot of very specific questions concerning the use of predictive methods with KNIME. I will include a few links to past discussions that also contain links to articles about evaluation metrics and example workflows.

Your questions suggest to me that you might benefit from making yourself familiar with some basic concepts of predictive model building. For example with this e learning course

https://www.knime.com/knime-introductory-course/chapter6

And if you want to get deeper into it there is a full blown Udemy course about KNIME that also covers Data Mining:

https://www.udemy.com/knime-bootcamp/

And then of course there is the KNIME forum to help you with further questions :slight_smile:


Models for 0/1 or Yes/No Targets:

Understand metrics like AUC and Gini (and use H2O.ai)

2 Likes

This topic was automatically closed 182 days after the last reply. New replies are no longer allowed.