The workflow begins by loading the GroupByFeatureTest.csv dataset, which includes user ID, purchase date, purchase amount, product category, and date of birth. The Feature Engineering node groups data by user ID and computes various metrics, including the number of purchases per user, days since the last transaction, average time between purchases, total purchase value, and customer age derived from the date of birth. The processed dataset, enriched with these user-level statistics, is then displayed using the Print N Rows node for verification and exploration.

It enables scalable, data-driven segmentation and customer analytics by summarizing purchasing behavior efficiently.