Group "like" rows together

Hello! Long time listener, first time caller here. I have a dataset of orders in a warehouse that I need to find correlation in based on the product needing to be picked for each of those orders.

For example, if Order A needs products 1, 2, 4, and 7, and Order B also needs products 1, 2, 4, but then 6 and 9, I want to somehow group or show a correlation ranking between those orders.

Below is a screenshot of where im at now in the analysis.

After the “groupby” node, I have tried several different methods to bin the orders together in groups of 8 using correlation but don’t seem to have enough logic built in to group them effectively.

Where should I start?

Thank you!!

You’re more likely to get some help if you can share some data and your current workflow. Also, what do you mean by “bin the orders together in groups of 8?”

1 Like

Not 100% sure based on what you posted here, but sounds like it might be useful for you to take a look at Market Basket Analysis: Market basket analysis – KNIME Community Hub

2 Likes