Penerapan Data Mining Untuk Prediksi Pola Pembelian Pelanggan Menggunakan Algoritma Apriori (Studi Kasus: Toko Jihan)

Abstract

Determining the combination of items and the layout of goods based on consumer purchasing trends is one solution for Toko Jihan in developing marketing strategies so as to increase sales at the store. The algorithm that can be used to find any combination of items that are often purchased together at a time is the Apriori Algorithm, the apriori algorithm is a market basket analysis algorithm used to generate association rules, with an "if then" pattern. In the apriori algorithm, frequent itemset-1, frequent itemset-2, and frequent itemset-3 are determined to obtain association rules from previously selected data. To get the frequent itemset, each data that has been selected must meet the minimum support and minimum confidence requirements. In this study using different minimum support and minimum confidence comparisons based on existing transaction data using a minimum support of 20% and a minimum confidence of 80% resulted in four association rules. One example is if the consumer buys cooking oil, coffee then 87% (certainty of consumers in buying items) will buy eggs.

Keywords: Association Rule Mining, Apriori Algorithm, Support, Confidence.