Implementation of Recency Techniques Monetary and K-Means for the Consumer Segmentation System

Business competition is a common thing among the people. Various methods and ways to be able to increase sales success production of both goods and services. Observation, survey, open marketing are one of various methods to be able to analyze the specific demands and needs of consumers. Not a few sellers who fail to attract interest and the attractiveness of consumers for not being able to conduct surveys to consumer needs that develop dynamically from time to time. In this study, Recency Monetary Frequency (RFM) technique was chosen to see the attractiveness and needs of consumers and the K-means clustering process is carried out in order to be able to group consumers based on financial level, shopping frequency and time of purchase. The dataset used for this research comes from UCI Machine Learning Repository. The results of this study indicate that the highest silhouette value with 2 clusters has an effect on the results of clustering the RFM value compared to the lowest silhouette value with more clusters. This system can be useful for sellers to be able to find out the habits of consumers and consumers who are the target of marketing.