Optimization E-Commerce Consumer Segmentation Based On K-Means Clustering And Machine Learning

The rapid growth of e-commerce in Indonesia has driven the need for more targeted marketing strategies. Consumer segmentation is an effective approach to understanding purchasing behavior. This study implements the K-Means Clustering algorithm, an unsupervised machine learning method, to perform consumer segmentation based on e-commerce product data. The dataset was obtained from the Kaggle platform, with key features including product ratings, prices, and sales volume. The number of clusters is determined automatically using the Silhouette Score method to achieve optimal segmentation. The segmentation results are visualized through a web-based application using Streamlit, allowing users to easily explore the characteristics of each cluster. Each cluster is analyzed to provide insights into consumer behavior and potential marketing strategies. This study demonstrates that a data-driven approach using machine learning can be effectively applied to support business decision-making in the e-commerce domain