Optimizing Inventory Management: Data-Driven Insights from K-Means Clustering Analysis of Prescription Patterns

Purpose: The goal is to improve how inventory is managed in healthcare by using K-Means clustering to analyze prescription trends. This approach helps ensure better stock availability, streamlines operations, and ultimately increases sales opportunities. Methods: This research applied the K-Means clustering algorithm to analyze a comprehensive dataset of prescription behaviors from XYZ Clinic. By grouping similar prescriptions into clusters, this method highlighted patterns within the data. These insights led to the identification of unique prescription categories, enabling the creation of tailored recommendations for improving inventory management. Result: The analysis showed that Cluster 1 should be prioritized for inventory management due to its high sales potential and consistent prescription patterns. It is recommended to increase stock for the medications in Cluster 1 to improve inventory turnover and streamline clinical operations. These findings underscore the value of K-Means clustering in healthcare, especially for enhancing inventory management and operational efficiency. Novelty: This research presents a novel application of K-Means clustering in healthcare, focusing on prescription patterns and inventory management. While previous studies have primarily used K-Means clustering for areas such as risk assessment and logistics, this study provides valuable data-driven insights to improve inventory management strategies in healthcare. The results highlight how clustering methods can support better decision-making and resource allocation, ultimately leading to greater operational efficiency and improved patient care.