Data Analytics Techniques in Supply Chain Management: A Systematic Review of Models, Applications, and Research Directions

Abstract

This review investigates the role of data analytics in supply chain management (SCM), synthesizing findings from 92 peer-reviewed articles publishe between 2010 to 2024. A structured taxonomy is presented, classifying analytics into six types: descriptive, diagnostic, predictive, prescriptive, real-time/streaming, and hybrid lifecycle analytics. These are mapped to key SCM functions such as demand forecasting, inventory management, logistics optimization, and supplier assessment. The analysis highlights the growing adoption of predictive and prescriptive models, while noting that descriptive tools remain dominant in practice. Key gaps include limited empirical validation, underutilization of advanced analytics in SMEs, and lack of cross-functional integration. Emerging trends include hybrid AI models, real-time decision systems, and sustainability-focused analytics. This study contributes a unified framework for understanding and deploying analytics in SCM, and outlines directions for future research in areas such as digital twins, analytics democratization, and multi-tier collaboration.