A model for sector restructuring through genetic algorithm and inverse DEA

Abstract

The aim of this study is to devise a sector restructuring model in which all the decision making units (DMUs) satisfy a predefined global efficiency level. The proposal makes several realistic assumptions regarding the merging of DMUs under specific circumstances. The model computes the global efficiency target by giving preference to merging DMUs over saving inputs, hence considering that the affected stakeholders may be resistant to restructuring, and this resistance may have overall negative effects on the image and reputation of the companies and organizations. In addition, the number of constituents in the new entities can be limited by the decision maker after the restructuring process, so that the model also considers a constraint on cardinality. The proposal combines the inverse data envelopment analysis (InvDEA), which computes the merger’s input savings, and the genetic algorithm (GA), which solves the combinatorial problem of identifying the merging units. The proposal is illustrated by two examples from banking and higher education.