Given the inherent benchmarking capability of DEA against best practices, we focused primarily on comparing the improvement targets generated by two DEA models: the conventional additive (ADD) model and the least-distance model. This analysis is performed using a time-series dataset comprising 86 retail companies in Japan. The main contributions of this study are summarized as follows.We conduct a comparative analysis between the improvement targets generated by the conventional ADD and the least-distance models.We investigate the effectiveness of the improvement targets generated by the two types of models by evaluating the efficiency of these targets in the subsequent year.Based on the results of the numerical experiments and analysis, it appears that the easy-to-achieve improvement targets generated by the least-distance model demonstrate higher effectiveness.Further exploration of improvement targets generated by other variations of the least-distance DEA models would be beneficial through additional numerical experiments using real-world or simulated data. Additionally, conducting empirical studies by applying the least-distance DEA models to diverse fields for efficiency improvement would contribute to the existing body of research.

The efficacy of DEA in efficiency measurement is the primary reason why DEA has gained significant attentions from researchers across the world. The primary benefits of DEA include its ability to provide both efficiency scores and improvement targets for decision making units(DMUs) under measurement. The improvement targets suggest several ways to improve inefficient DMUs’ efficiency. An improvement target that is close to the DMU under measurement is considered to be easy-to-achieve in DEA. However, in previous studies, most conventional DEA models used for China’s efficiency measurement provided a far improvement targets that cannot be achieved immediately and would require several years. Thus, a least-distance DEA model that can provide a closer improvement target is used in our study. Furthermore, a conventional DEA model and a ratio type DEA model are used to study and compare the performances. All three DEA models are applied to the measurement of China’s energy efficiency in 1997, 2002, 2007, and 2012. The differences in the efficiency scores and improvement targets provided by the three models have been reviewed. Although the results show different improvement targets, it can be inferred that reducing the overall energy consumption and increasing the GDP are still two effective measures for inefficient provinces, districts, and cities according to the experimental results. 

Data envelopment analysis (DEA) is widely used to evaluate and improve the relative efficiency of decision making units (DMUs), which have multiple inputs and outputs. However, traditional DEA models can only handle a single perspective. We proposed a new approach for efficiency improvement under multiple perspectives based on the least-distance DEA.  The Nash bargaining game (NBG) theory has been used in extant studies to avoid conflicts and obtain a rational direction of efficiency improvement under multiple perspectives. Because of the practicality of the closest efficient target, we first proposed a least-distance DEA model incorporating NBG. A numerical experiment is conducted to compare the performance of our proposed approach with that of previous studies. The results reveal that our proposed approach can (1) evaluate the efficiency of DMUs under multiple perspectives, and (2) provide more easy-to-achieve efficiency improvement suggestions for the assessed DMUs. Thus, the proposed approach has remarkable potential applicability in decision making.

Data envelopment analysis(DEA) has been widely applied to evaluate relative efficiency and provide benchmarking information(efficient target) for decision making units(DMUs). Recently, the least-distance DEA has been extensively researched, and various corresponding models are proposed because of the practicability of the least-distance benchmarking information(closest efficient target). We have formulated the least-distance range adjusted measure (LRAM), which satisfies a set of desirable properties, as a new practical DEA model for efficiency evaluation and benchmarking. Based on more numerical experiments and deeper analysis, we found (1) that efficient targets provided by the LRAM match the evaluated DMUs more closely than those provided by the convention range adjusted measure(RAM) for most of the inputs and outputs, (2) although LRAM may suggest modifying a greater number of inputs and outputs than that suggested by the RAM, it optimizes the input-output modification to significantly reduce the total percentages of modifications required for each of the inefficient banks to achieve efficiency. Thus, the LRAM suggests the required modifications to achieve efficiency in a more equitable and balanced manner.

Dataenvelopment analysis (DEA) introduced in 1978 has been widely applied toevaluating the relative efficiency and providing efficient target for decisionmaking units (DMUs). The conventional range adjusted measure (RAM) in DEA actsas a well-defined measure satisfying a set of desirable properties, especiallythe strong monotonicity. However, because of the practicality of the closestefficient target, we focus on formulating the least-distance range adjustedmeasure (LRAM) and proposing the use of an efficient mixed integer programming(MIP) approach to compute it. Our formulated LRAM: (1) satisfies the desirableproperties as the conventional RAM; (2) provides the least-distance benchmarkinginformation for inefficient DMUs, which will make the efficiency improvementeasy, and (3) can be computed easily by using the proposed MIP approach. Here, weapply the LRAM to a Japanese banking data set corresponding to the period 2017-2019.Based on the results: the LRAM generates higher efficiency scores and allowsinefficient banks to improve their efficiency with a smaller extent ofinput-output modification than that required by the RAM, which indicates thatthe LRAM can provide more easy-to-achieve benchmarking information for inefficientbanks. Therefore, from the perspective of the managers of DMUs, we provide a valuableLRAM for efficiency evaluation and benchmarking analysis.