Implementation Of Data Mining Sales Of Household Furniture At Smart Kitchen Shop Using The Method K-Means

Abstract

Household furniture is an item that is very much in demand by many people, especially mothers, the higher the number, the more demand. To get the desired information so that a store can sort out the inventory that must be met. So it takes a prediction for the sale of furniture products that are most requested by consumers which aims to facilitate the provision of stock goods. The purpose of this research is to apply data mining to determine what products or goods are most in demand, moderately desirable, less desirable. From the various data that the authors observe at the Smart Kitchen Store, namely the Smart Kitchen Store, it is still difficult to predict product inventory in the future. With this problem, we need to group the data based on the characteristics of product sales. In the grouping process, a grouping method will be used using the K-Means Algorithm as a manual calculation method and in its implementation a data mining software using RapidMiner Studio version 7.1 will be used.The results of the study consisted of 3 clusters, namely, 42 Most Interested Products (Double Stan Hangers, Napkins, and Stainless Dish Racks), 46 Moderately Interested Products (Super Mop Floor Mops, Surpets, and Electric Grater) and 32 Less Interested Products (Shower Hood 4 stacking, Ring Light, and stainless hood). at the Smart Kitchen Store, so that the data is used as a reference for the Smart Kitchen Store to manage the stock of goods so that the store does not disappoint customers because the goods or products you want to buy are not available.