Medicine Inventory Grouping using Clustering Data Mining

Abstract

One of the main factors in health services is adequate medicine supplies. Puskesmas is one of the health services that is managed under the district and city health offices to serve patients every day. However, there are obstacles in the process of medicine supply at the Puskesmas. Puskesmas still uses medicine supply techniques manually by looking at the minimum medicine stock. In this way, many medicines are unused and even lacking. The application of data mining can be used as an analysis to determine the medicine supply according to the patient's needs. In the data mining method, the clustering algorithm is one of the most popular to use where the data belonging to the same cluster will be close to each other and will be far from the data about another cluster. For this reason, this study used clustering to classify types of medicines based on the number of medicine uses and requests. The results are obtained in the form of information on the type of medicine with rapid use and model of m with extended usage every month taken from three years of data. Also, information on the types of medicines from the clustering process can be used to improve better patient service.

Keywords

• data mining
• clustering
• k-means algorithm
• stock
• medicine