Santoso, Jeffri
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Data Science Insights

Cluster Analysis of Superstore Data using K-Means and K-Medoids for Product Delivery Insights Sarumaha, Intan chintia; Foureshtree, Ajeng Cahyani; Jocelyn, Angela; Santoso, Jeffri; Hutabarat, Fernando
Data Science Insights Vol. 3 No. 2 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i2.34

Abstract

It is difficult to overcome the challenge of understanding the relationship between consumer patterns and overall market trends and improve the company's operational efficiency through optimizing the delivery process. Utilizing sales data from Super Store available on the Kaggle website, this study aims to identify predictable consumer patterns using cluster analysis, as well as explore how to improve delivery efficiency based on a better understanding of consumer needs and preferences. This research utilizes K-Means and K-Medoids clustering methods to group product subcategories into three categories: best-selling, in-selling, and not-selling. The process of data transformation, exploratory analysis, model building, as well as cluster performance evaluation were conducted with the help of analytical tools such as Microsoft Excel, Tableau, and RapidMiner. The results show that the K-Medoids algorithm provides more accurate clustering performance compared to K-Means, with a Davies-Bouldin Index value of -0.867 for K-Medoids and -0.519 for K-Means. This shows that K-Medoids is more suitable in describing the characteristics of existing data. The most in-demand cluster results are in the sub-category of machines and copiers products.