<![CDATA[The rapid development of e-commerce in Indonesia necessitates recommendation systems that can capture user purchasing patterns accurately, adaptively, and in a data-driven manner. This study implements the FP-Growth algorithm to analyze transaction data from a self-developed essential-goods e-commerce platform. The research dataset consists of 60 user accounts with a total of 600 completed transactions, processed using a Python-based analytical module and au-tomatically integrated into a Laravel backend through a dedicated execution script. The FP-Growth algorithm is applied to generate frequent itemsets and association rules using a min-imum support of 0.01, a minimum confidence of 0.1, and a minimum lift of 1.0. The results indi-cate that the most dominant associative patterns occur among kitchen staple products such as in-stant noodles, chicken eggs, and wheat flour, as well as household cleaning products such as de-tergents and fabric softeners. Several rules exhibit confidence values as high as 0.9615 and lift values up to 4.451, indicating strong and statistically significant relationships between products. System performance evaluation using a Top-4 recommendation scheme shows a Hit Rate of 54.35% and a Recall of 54.35%, demonstrating that the system is able to provide relevant recom-mendations for the majority of transactions. This implementation is shown to improve recom-mendation accuracy while strengthening personalization and cross-selling strategies on essen-tial-goods e-commerce platforms. These findings confirm that FP-Growth is an effective and effi-cient method for identifying empirical purchasing patterns and supporting the development of recommendation systems in small- to medium-scale e-commerce environments.]]>
