The decision-making units (DMUs) in the modern service industries may produce desirable outputs and undesirable outputs. For the decision makers, some outputs may be more desired than others although all of them are desirable. Considering these characteristics, this work combines the data envelopment analysis (DEA) and the multiple attributes decision-making (MADM) method, to make a reasonable and comprehensive performance evaluation for DMUs. Specifically, three DEA-based models are modified to obtain more reasonable efficiency scores for DMUs. The MADM method is used to determine the weights of outputs based on the preference ratings within the outputs. The efficiency scores are then multiplied by the aggregated outputs quantities to obtain the comprehensive performance scores for evaluation. The effectiveness of the proposed models is demonstrated by extensive numerical experiments.

现代服务业中的决策部门（DMU）可能会产生理想的产出和不良的产出。对于决策者来说，尽管所有输出都是可取的，但与其他输出相比可能更需要一些输出。考虑到这些特性，这项工作结合了数据包络分析（DEA）和多属性决策（MADM）方法，对DMU进行了合理，全面的性能评估。具体来说，对三个基于DEA的模型进行了修改，以获得DMU的更合理的效率得分。MADM方法用于根据输出中的优先级确定输出的权重。然后将效率得分乘以合计的输出数量即可获得综合性能得分以进行评估。