Application of the Association Method Using FP-Growth Algorithm to Find Pattern Of Medicine Purchasing Transactions at Pharmacy

Abstract

This research was conducted with the aim of finding patterns of medicine sales transactions at the Family Pharmacy so that it can be used as a reference for providing medicine stock so that service to consumers can be improved. This study uses the association method by implementing the FP-Growth algorithm. Through the association method, patterns of medicine purchases will be found in the form of medicine that are purchased together. Then, this study wants to test the FP-Growth algorithm in finding patterns of medicine purchases. The data used is data for the second half of 2021. This dataset consists of 20,266 transactions and 1,166 attributes in the form of medicine. The results of the study by setting different minimum support and minimum confidence values, 7 association rules are obtained with a minimum support value of 10% and a minimum confidence of 90% and the accuracy value of each rule formed is 2,683. The level of association rules formed is strong because it shows more than 1. After knowing the association rules that are formed, these rules will be used as a reference in providing medicine stocks and medicine recommendations.