Multi-Criteria Decision Making in Inventory Classification

Inventory classification has traditionally relied on single‐criterion methods, most notably the ABC approach, which ranks items by annual usage value alone. In contrast, multi‐criteria decision making (MCDM) frameworks allow decision makers to assess each stock‐keeping unit against a range of dimensions, such as demand variability, lead time, criticality, cost, risk exposure and sustainability indicators. By integrating weighting techniques from operations research (for example, linear programming, Analytic Hierarchy Process and Full Consistency Method), fuzzy set theory and advanced data‐driven models, modern classification systems produce more nuanced groupings. These produce tailored replenishment rules, service‐level targets and resource allocations. Recent advances span explainable artificial intelligence (XAI) to demystify black‐box sorting models, group decision protocols to capture stakeholder perspectives, and sensitivity analyses to gauge the robustness of classifications. Such approaches support global supply chains in adapting to volatility, improving service reliability and optimising working capital across manufacturing, retail and spare‐parts networks.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Research from all publishers

A two‐phased explainable artificial intelligence approach has been applied to ABC item classification, combining local and global XAI techniques. By revealing which sales, profit and customer‐priority metrics drive each category assignment, managers gain transparency into automated sorting rules while maintaining high classification accuracy.

An integrated fuzzy MCDM model merges the Full Consistency Method with both a distance‐based evaluation and a classical ABC analysis. Through trapezoidal membership functions and extensive sensitivity testing, this framework delivers smoother transitions at category boundaries and enhances cost‐efficiency in procurement and service‐level decisions.

A collaborative inventory control methodology unites value‐chain analysis with the Analytic Hierarchy Process in a group decision‐making setting. Stakeholders from procurement, operations and finance jointly define and weight criteria, yielding consensus‐driven ABC classifications that improve communication, accountability and system performance in distributed logistics environments.

Multi-Criteria Decision Making in Inventory Classification publication trend

The graph below shows the total number of articles in multi-criteria decision making in inventory classification across all publications each year (not limited to Nature Index journals).

Technical terms

Multi‐Criteria Decision Making (MCDM): A structured approach to compare and rank alternatives by considering multiple, often conflicting, decision criteria.

ABC classification: A tiered inventory sorting technique that groups items into A, B or C categories based on their relative importance across selected metrics.

Fuzzy set theory: A mathematical framework in which elements may belong to categories with varying degrees of membership, permitting flexible classification thresholds.

eXplainable Artificial Intelligence (XAI): Methods and tools designed to make the decision processes of complex AI models transparent and understandable to human users.

Analytic Hierarchy Process (AHP): A decision‐support tool that decomposes complex choices into pairwise comparisons to derive relative weights for each criterion.

References

1. An Explainable Artificial Intelligence Approach for Multi-Criteria ABC Item Classification. Journal of Theoretical and Applied Electronic Commerce Research (2023).
2. A New Model for Stock Management in Order to Rationalize Costs: ABC-FUCOM-Interval Rough CoCoSo Model. Symmetry (2019).
3. Improving Distributed Decision Making in Inventory Management: A Combined ABC‐AHP Approach Supported by Teamwork. Complexity (2020).