Multiple criteria ABC classification: an accelerated hybrid ELECTRE-PSO method

ABC classification analysis categorises inventory items into predefined classes namely A, B and C. The limitation of the ABC system is that only one criterion is considered, however, as emphasised in the literature, the inventory classification is multi-criteria problem. So, this paper proposed a multiple criteria ABC inventory classification (MCIC) method integrating ELECTRE TRI with particle swarm optimisation (PSO) algorithm. Since, the application of ELECTRE TRI method requires to determine the preferences of decision makers (DMs) as parameter values, the solution process is very complex and time-consuming especially in large-scale problems. Tackling these difficulties, all ELECTRE TRI parameters are inferred from training data through a procedure using hybrid PSO algorithm, for accelerating the PSO, the variable position (VP) model is also proposed as an exploitation and variable exploration. Finally, the model applied to six inventory datasets and the results revealed high applicability of the proposed model to inventory classification problems.