ABC analysis using Particle Swarm Optimization and its performance evaluation with other models

Purpose: The purpose of this article is to develop a cost-effective model for Multi-Criteria ABC Inventory Classification and to measure its performance in comparison to the other existing models. Design/methodology/approach: Particle Swarm Optimization (PSO) algorithm is exclusively designed for Multi-Criteria ABC Inventory Classification wherein the inventory is classified based on the objective of cost minimization, which is achieved through the inventory performance index – total relevant cost. Effectiveness of classification of the proposed model and the other classification models toward two inventory performance measures, that is, cost and inventory turnover has been computed, and the results of all models are relatively compared by arriving at the cumulative performance score of each model. Findings: This study reveals that the ABC Inventory classification based on the proposed PSO approach is more effective toward cost and inventory turnover ratio in comparison to the twenty existing models. Practical implications: The proposed model can be easily adapted to the industrial requirement of inventory classification by cost as objective as well as other inventory management performance measures. Originality/value: The conceptual model is more versatile which can be adapted for various objectives and the effectiveness of classification in comparison to the other models can be measured toward each objective as well as combining all the objectives.