Providing a New Model to Improving DEA-based Models in Multi-criteria Inventory Classification (Case Study: Pars Khazar)

Many organizations use the ABC classification method to control their large amount of inventories. The most common way to classify inventories is the ABC method. In traditional ABC classification, items are only classified according to one criteria. But there are other criteria that need to be considered in the inventory classification. The purpose of this study is to present a new model for multi-criteria inventory classification. Among the multi-criteria inventory classification methods, DEA-based methods do not require decision makers to determine the weight of the criteria; however, in the literature, only the radial methods of data envelopment analysis are used to classify inventory items. In this paper, the cross-efficiency of a non-radial model is proposed in order to improve the average cross-efficiency of the R model, which is a radial model. Therefore, the proposed method does not have the weakness of R model due to the use of a non-radial model and also it has benefits the cross-efficiency method. The models were executed on 47 items of inventory related to a common numerical example in the research literature as well as on 80 items of inventory of the Pars Khazar Industrial Company and the results of the implementation of the models have been analyzed. The results of comparing the proposed model with some of the existing models in the literature indicate the superiority of the proposed model.