An inverse data envelopment analysis model to consider ratio data and preferences of decision-makers

Abstract

Inverse data envelopment analysis (DEA) determines the optimal level of inputs and/or outputs of decision-making units (DMUs) to reach efficiency targets. This paper presents a new inverse DEA model for determining minimum inputs for working capital management. The proposed model is employed in the Indian textile industry to calculate working capital efficiency. Given the working capital efficiency, the decision maker’s preferences will be estimating the change in inputs when outputs increase. Furthermore, unlike the standard inverse DEA model, this article discusses the inverse DEA model when negative ratio data exists. The DEA model requires additional attention when ratio data are present; therefore, a novel inverse DEA ratio model is proposed. The input targets obtained from the proposed model are less than the standard inverse DEA model. Also, the proposed model is a closer estimate of the production probability set for ratio data.

Estimating outputs using an inverse non-radial model with non-discretionary measures

“…Sohrabi et al [28] assessed inputs/outputs using an inverse DEA-R approach with ratio data. Afterwards, Mahla et al [25] used an inverse DEA ratio technique and assessed input variations when there were negative ratio data. As a review of the inverse DEA literature shows, there is no inverse DEA model based on non-radial forms to estimate outputs (inputs) while presenting non-discretionary inputs.…”