Clustering customers based on purchases

jhurliman

I have a simple CSV file that looks like this:

CustomerID,ItemID
1,50
1,37
1,38
2,37
3,45
4,19
...

My goal is to cluster customers to learn different categories of customers based on overlapping purchases. So far I have a Read CSV operator that assigns both columns as nominal attributes, fed into a Pivot operator that sets group attribute to CustomerID and index attribute to ItemID. Am I on the right path? What clustering approach should I use for this purpose?

Thank you in advance for your help.