<![CDATA[ The development of information technology has resulted in a significant increase in data volume, including in the healthcare and pharmaceutical sectors. Drug sales transaction data stored in the information systems of pharmacies, hospitals, and other healthcare facilities has the potential to be used as a basis for decision-making through the application of data mining techniques. This study aims to conduct a literature review on the application of various classification algorithms in data mining-based drug sales analysis. The research method used is a Systematic Literature Review (SLR) with the stages of problem identification, literature search, article selection, data extraction, and analysis and synthesis of research results. Literature sources were obtained from Google Scholar, Garuda, SINTA, and various relevant national and international journals. Based on the results of the review of articles published between 2020 and 2026, it was found that the algorithms widely used in drug sales analysis include Naive Bayes, Decision Tree C4.5, K-Nearest Neighbor (KNN), Neural Network, K-Means Clustering, Apriori, and FP-Growth. The results show that each algorithm has different characteristics and advantages according to the objectives of the analysis. Naive Bayes and C4.5 were effectively used for sales data classification, KNN was used for predictions based on historical data, K-Means was used for sales data clustering, while Apriori and FP-Growth were used to discover patterns of drug purchase associations. The results of this study indicate that the application of data mining can improve the effectiveness of stock management, drug distribution, marketing strategies, and support more accurate decision-making in the pharmaceutical sector.]]>
Copyrights © 2025
