Clustering Analysis Approach to Enhance Inventory Management and Product Recommendations in the Ornamental Plant Industry
Year: 2024
Type: article
Abstract: The ornamental plant industry has grown significantly as consumers seek to enhance living spaces with diverse plant species. This study aims to optimize inventory management and marketing strategies by applying K-Means clustering to categorize plants based on price, pot size, light requirements, care levels, and popularity. The method used is K-Means clustering, which groups plants into three clusters based on key characteristics. By analyzing these attributes, K-Means clustering identifies patterns and similarities among different plant species, allowing businesses to understand consumer preferences and inventory management better. The results identified three main clusters: Cluster 1 (moderate care, light, popularity) plants like Aglaonema require balanced stock and targeted promotion for medium-light environments. Cluster 2 (low care, light, popularity) plants such as Aglaonema Chiangmai need high stock levels and budget-friendly marketing. Cluster 3 (high care, light, popularity) plants like Alocasia demand elevated stock, premium quality, and care-focused promotion.
Authors: Muhammad Iqbal Faturohman, Thalia Naziha
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4406001558