<![CDATA[Sales transaction data is something that can be reused for business decision making. However, in this case, the transaction data is not reused for business purposes, and is only used as an archive of sales reports. The FP-Growth algorithm is a level of a priori association algorithm that uses alternative itemset frequencies based on the numbers that most frequently appear in each transaction (frequent itemset) in a group of data. The characteristic of the FP-Growth algorithm is that the structure of the data used is a tree with the name FP-Tree. With the use of FP-Tree, the FP-Growth algorithm can extract frequent Itemsets from FP-Tree. The FP-Growth method is divided into 3 main stages, namely the conditional pattern base generation stage, the FP-Tree conditional generation stage, and the frequent itemsset search stage. With the application of the FP-Growth method in this study, it can be used to see product sales patterns. The results obtained are in the form of 5 interesting rules by entering a min support value of 10% and min confidance 50%, namely if you buy diapers then buy clothes, if you buy a pacifier baby then buy clothes, if you buy hats then buy clothes, if you buy pants you will buy clothes, and if you buy a singlet you will buy clothes. It is hoped that this research can help Aura Moms Baby & Kids Retail owners in utilizing the results of sales transactions so that the results can be utilized appropriately. This is evidenced by the creation of an E-Business system that can manage sales transactions to determine product purchase patterns at Retail Aura Moms, Baby & Kids.]]>
Copyrights © 2023
