A hybrid approach using two-level DEA for financial failure prediction and integrated SE-DEA and GCA for indicators selection

Abstract

Corporate financial failure prediction is playing an increasingly important role for both shareholders and companies. There are many different approaches that have been developed over the years. The aim of this paper is to introduce a new data envelopment analysis (DEA) model that is a two-level DEA as a quick and feasible tool for corporate financial failure prediction, which is able to handle quite a large number of inputs and outputs by utilizing hierarchical structures of financial indicators. To use the two-level DEA model, we need to select high relevant indicators from a large set of candidate indicators as inputs and outputs, which is not trivial. So the approach that integrates the super-efficiency DEA (SE-DEA) and the grey relational analysis (GRA) is introduced to select financial indicators that have more meaningful correlations with the corporate financial situation from a lot of indicators. The results of empirical analysis conducted on companies listed in Shenzhen Stock Exchange Market (SSEM) of China demonstrate the advantage of the two-level DEA and the integrated SE-DEA and GCA over the CCR and the BCC.