Abstract— Classification of drug data in an agency engaged in
the health sector is very important. This activity cannot be separated
from supervision and monitoring every day because the processing
of drug data is the core of the wheels of business in an agency or
company. This research was conducted to discuss the importance of
data processing in an agency or company, namely the Sawah Besar
District Health Center. Currently the problem that occurs is the
absence of a method in classifying drug data. Drugs have not been
grouped according to their characteristics so that it becomes an
obstacle when searching for data and when checking stock. With the
above problem we need a method. One is by using the K-means
algorithm method. K-means clustering is a non-hierarchical cluster
analysis method that seeks to partition existing objects into one or
more clusters based on their characteristics. These drug data are
classified into 4 categories, namely over-the-counter drugs, limited
over-the-counter drugs, hard drugs, and narcotics & psychotropics.
. The results of the research that has been done are that by using the
K-Means algorithm the Sawah Besar District Health Center can
classify drug data with high, moderate to low use levels based on the
volume of use and intake. The data taken from the Sawah Besar
District Health Center is drug stock data in December 2021. Manual
calculations get an accuracy of 66.23% for cluster 1, 7.69% for
cluster 2, and 23.07% for cluster 3 on over-the-counter drug data
limited.