Penerapan Algoritma K-Medoids Dalam Klasterisasi Penjualan Laptop

Abstract

Technological developments have made the use of laptops a basic necessity that must be owned to assist in completing a job as a substitute for a PC (Personal Computer). Along with technological advances, many laptop brands have sprung up, from each brand to launch laptops with various advantages. This has resulted in more and more emerging various types of laptop brands that compete with each other to be able to meet the needs of today's consumers. Therefore there must be a system that can provide advice or laptop recommendations in searching for references. This study aims to classify laptop sales data using the k-medoids clustering algorithm data mining method. laptop sales data are grouped based on the similarity of the data so that data with the same characteristics will be in one cluster. Based on the calculations that have been carried out by researchers on 1000 sample data, it can be categorized into 3 clusters. cluster 1 is a category of low laptop sales, which is 137 data, then cluster 2 is a category of high laptop sales, which is 669 data, and cluster 3 is a category of medium laptop sales, which is 194 data from 1000 categories of laptop sales. It can be concluded that the grouping of laptop sales data in cluster 2 is the most widely sold because the specifications and prices of laptops are more affordable than cluster 1 and cluster 3. And it has been tested using the Rapid Miner application with the same results as manual calculations using Microsoft Excel.

Keywords: K-Medoids, Clustering, Laptop Sales