Analysis of Consumer Purchase Patterns on Google Merchandise Store E-Commerce Using Apriori Algorithm to Support Marketing Strategies

Abstrak

The development of e-commerce generates large amounts of transaction data that can potentially be used to support data-driven marketing strategies. This study aims to analyze consumer purchase patterns in the Google Merchandise Store dataset using the Association Rule Mining method with apriori algorithm. The dataset used consisted of 12,267 transactions with 382 product attributes transformed into a binary incidence matrix. The parameters applied are a minimum support of 0.005 and a minimum confidence of 0.05. The results of the analysis resulted in seven association rules that met the threshold. The rule with the highest confidence shows that 47.1% of consumers who buy Android Sticker Sheet Ultra Removable also buy Google Laptop and Cell Phone Stickers. These findings indicate the existence of product linkages that can be used for cross-selling and product bundling strategies. Overall, the apriori algorithm has proven to be effective in identifying consumer purchasing patterns as well as supporting data-driven marketing decision-making on e-commerce platforms.