DEA cross-efficiency evaluation based on Pareto improvement

摘要: Abstract Cross-efficiency evaluation, as an extension tool of data envelopment analysis (DEA), has been widely applied in evaluating and ranking decision making units (DMUs). Unfortunately, the cross-efficiency scores generated may not be Pareto optimal, which reduced effectiveness this method. To solve problem, we propose a evaluation approach based on improvement, contains two models (Pareto optimality estimation model improvement model) algorithm. The is used to estimate whether given set are Pareto-optimal solutions. If these then make for all DMUs. In contrast other approaches, our always obtains cross efficiencies under predetermined weight selection principles addition, if proposed algorithm terminates at its step 3, results by unify self-evaluation, peer-evaluation, common-weight-evaluation DEA evaluation. Specifically, self-evaluated efficiency peer-evaluated converge same common-weight-evaluated when stops. This will more likely accepted