Application of Artificial Intelligence Techniques: Hierarchical Clustering and K Means Algorithms in Optimizing Inventory Classification Methods in Economic Enterprises

This study aims to enhance the efficiency of inventory management in industrial enterprises by integrating traditional inventory classification methods with machine learning techniques. The methodology employed includes the application of ABC, XYZ, and VED analyses, as well as their hybrid combinations, in parallel with clustering algorithms namely, K-Means and Hierarchical Clustering on inventory data from the Luqman Mills company, used as a case study. The dataset comprises a variety of product items and was analyzed based on annual consumption, unit cost, and shortage cost.The results reveal that traditional methods offered relatively simplified classifications, while machine learning algorithms significantly improved the accuracy of pattern recognition. This enabled a more precise categorization of inventory items into three classes: high-priority (requiring strict monitoring), medium-priority (requiring periodic review), and low-priority (requiring basic oversight). The integration of these approaches led to a reduction in monitoring costs and better resource allocation. The study recommends extending the implementation of these methods to other industrial settings and stresses the importance of regular data updates to maintain classification accuracy.

• inventory classification
• inventory management
• ABC classification
• XYZ analysis
• VED analysis
• hierarchical clustering
• K-means clustering
• industrial enterprises

• 9 — الصناعة والابتكار والبنية التحتية

• Supply Chain and Inventory Management
• Data Mining and Machine Learning Applications
• Impact of AI and Big Data on Business and Society
• inventory classification
• inventory management
• ABC classification
• XYZ analysis
• VED analysis
• hierarchical clustering
• K-means clustering
• industrial enterprises
• Management Information Systems
• Information Systems
• Management Science and Operations Research
• Business, Management and Accounting
• Computer Science
• Decision Sciences