Multi-Dimensional Tail Classification in Procurement Spend Analysis: A Data-Driven Approach to Strategic Sourcing Optimization

Abstract

Effective procurement tail spend management rep-resents a significant opportunity for organizational cost optimization, yet identifying tail spend categories remains challenging due to the multi-dimensional nature of procurement data. This study presents a comprehensive analytical framework for classifying procurement tail spend using three distinct methodologies applied to a large industrial dataset of 24,983 transactions. Our analysis reveals that 88.5% of transactions exhibit tail characteristics under at least one classification method, with significant overlap across multiple dimensions. By employing F1-score evaluation, we identify 21 critical material groups representing 38.59% of transactions but only 9.56% of total spend value, achieving an F1-score of 0.65 and IoU of 0.48 against domain expert classifications. These findings demonstrate the importance of multi-dimensional analysis in procurement optimization and provide actionable insights for strategic sourcing initiatives in the aluminum manufacturing industry.

More by Magzhan Kairanbay

• End-to-End VITS Outperforms Two-Stage Tacotron 2 Synthesis for Kazakh: A Comparative Study on a New Multi-Domain Speech CorpusAlgorithms · 2026
• Vision-Language Temporal Analysis for Illegal Waste Dumping Detection in Surveillance VideosIEEE/CVF Winter Conference on Applications of Computer Vision Workshops · 2026 · Citations: 2
• Real-Time Multi-Parameter Petroleum Coke Quality Monitoring Using Computer Vision and Integrated Anomaly Detection for Aluminum Smelting OperationsInternational Conference on Computer and Applications · 2025
• LLM-Enhanced Semantic Clustering for Predictive Industrial Incident Detection: A Zero-Shot Approach to Safety AnalyticsIEEE ... International Conference on Data Mining workshops · 2025