A DEA model for two-stage parallel-series production processes

Abstract

Data envelopment analysis (DEA) has been widely used to measure the performance of the operational units that convert multiple inputs into multiple outputs. In many real world scenarios, there are systems that have a two-stage network process with shared inputs used in both stages of productions. In this paper, the problem of evaluating the efficiency of a set of specialized and interdependent components that make up a large DMU is considered. In these processes the first stage consists of two parallel components which are connected serially with the process in the second stage. The paper develops a DEA approach for measuring efficiency of decision processes which can be divided into two stages. This application of parallel-series production process involves shared resources and the paper determines an optimal split of shared resources among two components.