Analysis of K-Means Clustering Algorithm: A Case Study Using Large Scale E-Commerce Products
Norsyela Muhammad Noor Mathivanan, Nor Azura Md Ghani, Roziah Mohd Janor · 2019
E-commerce has become a crucial platform consists a large database of products with billions number of retailers and consumers. However, these products are placed into different categories according to the structure of different websites. A clustering analysis using K-Means Clustering algorithm helps in providing an insightful pattern on categories of clustered products. This analysis leads to an automatic classification model to classify the products efficiently. This paper presents a step by step cluster analysis using K-Means clustering to group e-commerce products from the online store website in Malaysia. The results show that the e-commerce products were categorized into three clusters. The most frequent words in each cluster provided a useful insight on the category of the clustered products which were hair and face, oral and pets care products. Hence, K-Means clustering analysis able to group a large data set of e-commerce products effectively.