PENERAPAN DATA MINING TERHADAP DATA PENJUALAN DENGAN MENGGUNAKAN ALGORITMA APRIORI PADA TOKO CITRA UTAMA

Abstract

Citra Utama Store is a retail and wholesale business aimed at meeting the needs of local residents for their daily household shopping. The problem lies in the difficulty of identifying consumer shopping trends for products in the store, and the inefficiency of the stock placement system. In a competitive business environment, it is crucial for us to obtain information that can help develop our business. One source of such information is the sales transaction history. Using data mining with the apriori algorithm and association rule, we can extract sales transaction data to derive information that can be used to identify frequent itemset combinations, which can then be analyzed to determine products frequently sold together, the most popular items, and customer preferences. The analysis of association rules formed from the apriori algorithm calculation yielded the highest itemset combination pattern, namely EGGS → AQUA GLN, with a support value of 2.84% and a confidence value of 34.13%. By setting minimum support >1.5% and minimum confidence >30%, this research can assist the store in devising sales strategies and managing stock inventory, and uncover association rules that can be used as purchasing patterns by consumers