Data-Driven Product Segmentation for Shallot Commodities using PCA and K-Means Clustering Approach

Abstrak

The shallot industry plays a strategic role in the Indonesian economy, especially in the Brebes Regency as the largest production center. However, challenges in the form of price fluctuations and low value-added products still burden farmers. Previous research tends to focus on individual products without considering a holistic product clustering strategy. This study aims to address the gap by applying the K-Means clustering method combined with Principal Component Analysis (PCA) to identify patterns in shallot and processed product sales data. The research data includes sales of 308 products from 2022-2024. The variables analyzed include product type, size, number of sold, and turnover. The results of the analysis formed three main groups, which are group 0 (small products with low performance), group 1 (large products with superior performance) and group 2 (medium products with stable performance). The findings indicate the importance of more targeted marketing strategies and product diversification. The implications of this study include optimizing superior products, revitalizing low-performing products, and developing stable products to expand the market. A customized e-Commerce-based strategy per cluster can improve the financial performance of the organization and the welfare of shallot farmers in a sustainable manner.