Development of Decision Support System for Duck and Chicken Culinary Businesses Based On Good Manufacturing Practices Using Data Mining

This study presents the development of a Decision Support System (DSS) for duck and chicken culinary businesses through the integration of Good Manufacturing Practices (GMP) and data-driven analysis using K-Means clustering and Association Rule Mining. The system processes production, nutritional, economic, and sensory data collected from processed poultry products to support business decision-making. K-Means clustering successfully segmented 32 samples into four meaningful product groups based on meat attributes, cooking characteristics, cost levels, and quality evaluations. The clustering results distinguished fast-cooking, low-cost chicken products from slow-cooked, high-cost duck dishes, revealing clearly differentiated culinary market segments. Association rules further identified strong correlations among product type, fat level, production cost, and cooking duration, providing valuable knowledge for identifying premium or mainstream culinary categories. When combined, the clustering and rule-based insights enhance GMP implementation by supporting standardization, quality control, and traceability throughout food preparation processes. The resulting DSS enables producers to optimize resource usage, refine menu strategies, and strengthen product consistency while aligning with food safety and hygiene standards. Overall, this research demonstrates that integrating GMP with AI-based analytics provides a practical and scalable approach for improving governance, operational efficiency, and competitiveness in small and medium-scale duck and chicken culinary enterprises.