Multi-stage Data Envelopment Analysis Model Research Articles

Performance analysis in a stochastic supply chain with reverse flows: a DEA-based approach

Abstract Traditional efficiency studies on network data envelopment analysis (DEA) consider decision-making units as black boxes that use a set of crisp inputs to produce a set of crisp outputs and that ignore intermediate measures and reverse flows. In real applications, however, we are faced with network systems with reverse flows in an uncertain environment. In this paper, therefore, a chance-constrained multistage DEA model is introduced to analyze the relative performances of supply chains and components in the presence of reverse flows and random factors. A real case in the sugar illustrates the proposed method. The results demonstrate the validity and applicability of the model.

A two stage data envelopment analysis model with undesirable output

The dependent relationship among the decision making units (DMU) is usually assumed to be non-existent in the development of Data Envelopment Analysis (DEA) model. The dependency can be represented by the multi-stage DEA model, where the outputs from the precedent stage will be the inputs for the latter stage. The multi-stage DEA model evaluate both the efficiency score for each stages and the overall efficiency of the whole process. The existing multi stage DEA models do not focus on the integration with the undesirable output, in which the higher input will generate lower output unlike the normal desirable output. This research attempts to address the inclusion of such undesirable output and investigate the theoretical implication and potential application towards the development of multi-stage DEA model.

Equivalent solutions to additive two-stage network data envelopment analysis

In the additive approach of two-stage network data envelopment analysis (DEA), the non-linear DEA model is transformed into a parametric linear model and then solved by computing a series of linear programs. Lim and Zhu (2013; Integrated data envelopment analysis: Global vs. local optimum.European Journal of Operational Research, 229(1), 276–278) and Ang and Chen (2016; Pitfalls of decomposition weights in the additive multi-stage DEA model. Omega, 58, 139–153) propose two parametric linear approaches to solve additive two-stage network DEA model. The current study shows that the two approaches are equivalent and use the same parameter in searching for the global optimal solution.

Efficiency pattern and spatial strategy of ports in Yangtze River Delta Region

This paper measures the efficiency of ports in the Yangtze River Delta Region (YRDR) in 2008 and 2013 using port berth quantity, quay length, and human resources as input indicators, using cargo and container throughput as output indicators, and considering traditional (foreign trade dependence and industrialization level) and modern environmental factors (traffic line density, financial development level, and informatization level). To achieve such aim, this study constructs a multi-stage data envelopment analysis model (DEA) that identifies effective port decision-making units (DMUs) and generates a highly accurate conclusion by eliminating the interference from the exogenous environment and random errors. First, the external environment significantly affects port efficiency, with the traditional environmental factors showing huge fluctuations and the modern environmental factors producing great benefits. Second, the efficiency of ports in YRDR has increased from 2008 to 2013 primarily because of their pure technical efficiency. Third, the weighted standard deviation ellipse (SDE) analysis results reveal that the efficiency pattern of ports significantly deviates from their throughput pattern, while the center of SDE of port efficiency moves from the eastern coastal regions to the northwest regions. Based on these findings, this paper proposes spatial development strategies for YRDR, such as creating an unblocked environment where spatial elements can freely circulate, intensifying port-city joint development, implementing differentiated policies, and focusing on the spatial collaboration of port efficiency.

Integrating multi-stage data envelopment analysis and a fuzzy analytical hierarchical process to evaluate the efficiency of major global liner shipping companies

ABSTRACTIn this study, we establish a multi-stage data envelopment analysis model to evaluate the efficiency of global liner shipping companies (LSCs). Because conventional solution procedures cannot guarantee the uniqueness of solutions, in this study, we specifically devise a new two-phase algorithm to overcome this problem. The first phase ranks the priority of all stages by applying fuzzy analytical hierarchical process. The second phase then solves the efficiency score for each stage according to its priority. We established and empirically tested a three-stage research model based on data collected from the Containerization International Year Book, the Alphaliner website and annual LSC reports for the year 2012. The results show that the proposed algorithm not only determines unique solutions for the efficiency scores but also determines the priority order of the stages involved in this process. Taking advantage of the proposed model and algorithm, LSCs can effectively locate bottlenecks in their production processes and further improve them by adjusting the values of the corresponding input and output variables. In addition, the priority order of the stages obtained from the empirical study can also help LSCs allocate their resources.

Implementing energy efficiency for target setting in the sugar industry of Iran

Sugar plants are one of the most energy-consuming industries in Iran; thus, the implementation of measures to improve energy efficiency seems necessary for such industries. This paper investigated sugar plants’ efficiency in different stages for implementation process of energy efficiency measures focusing on determining some relations for benchmarking and reaching efficient status. In doing so, the process of implementation of energy efficiency improvement measures is planned on the basis of experts’ opinions. Also, for deriving the efficiency of each plant in each of the stages of implementation of measures and the aggregate efficiency of them a multi-stage data envelopment analysis model is formulated. The obtained results from average efficiency indicated that the under evaluation population in the first, second, third, and fifth stages have a good performance and in the fourth-stage managers could not perform successfully. Also, the results of determining some relations for benchmarking showed that to what extent each of the outputs of each stage of the implementation process of energy efficiency measures in the sugar plants should be changed in order to achieve efficient conditions. The distance between the current output and the desirable output indicates to what extent manager has been successful in operation, studies of the rate of change of each of the outputs to achieve the efficient conditions are of the utmost importance in developing suitable strategies.

A dynamic multi-stage data envelopment analysis model with application to energy consumption in the cotton industry

Data envelopment analysis (DEA) is a non-parametric method for evaluating the relative efficiency of homogenous decision making units (DMUs) with multiple inputs and outputs. In this paper, we present a dynamic multi-stage DEA (DMS-DEA) approach to evaluate the efficiency of cotton production energy consumption. In the proposed model, the farms which consume resources (i.e., fertilizers, seeds, and pesticides) to produce cotton are assumed to be the DMUs. Inputs not consumed during a planning period are carried over to the next period in the planning horizon. Initially, a DMS-DEA model is used to determine the overall efficiency of the DMUs with dynamic inputs. Next, the efficiency score of each DMU is calculated for each time period in the planning horizon. We demonstrate the applicability of the proposed method and exhibit the efficacy of the procedures and algorithms with a real-life case study of energy consumption in the cotton industry.

Measuring efficiency of football teams by multi-stage DEA model

Original scientific paper Using the nonparametric variable output-oriented DEA (Data Envelopment Analysis) model, this paper analyses technical efficiency of the observed national football team in the qualifications for 2010 FIFA World Cup. If DEA model has a two stage structure, the first stage uses inputs to generate outputs that then became the inputs to the second stage. The indexes of efficiency, previously generated for attack and defence, will be implemented as parameters in the second-stage DEA analysis in accordance with the initial aim of this paper, to present new results as the outcome of the comprehensive approach to both inseparable aspects of the football. This theoretical approach is structured as follows: the football teams are defined as DMU (DecisionMaking Units), then, the methodology is established, specifically, the stages of range and objectives, analysis of procedure and variables, and the description of the theoretical analysis used.

Pitfalls of decomposition weights in the additive multi-stage DEA model

This paper examines limitations of the multi-stage DEA (data envelopment analysis) model in the literature. We focus on the DEA model with additive efficiency decomposition. We create taxonomy for the multi-stage DEA models and show when the decomposition weights can be non-increasing. When the decomposition weight for a stage is deemed reflective of the stage׳s relative importance, this property then implies that upstream stages (regardless the stage efficiency scores) in the model will obtain higher priority in efficiency decomposition. We also find that the non-increasing weights can affect the evaluation of overall and stage efficiency scores. We illustrate our findings through an empirical data set.

A data envelopment analysis approach to evaluate sustainability in supply chain networks

Benefiting from a performance measurement system is an inevitable necessity for any supply chain management to direct the business operations towards the maximal efficiency. In particular, there has been an increasing interest in incorporating sustainability practices evaluation in supply chain operations in the last years due to various stakeholders' requirements. The sustainability paradigm calls for balancing economic, environmental, and social needs. This paper focuses on the evaluation of supply chain operations that maximize economic returns, minimize environment impacts, and meet social expectations. In order to design a supervisory framework to measure the performance of these operations, this study develops a multi-stage data envelopment analysis model that is apt to evaluate the sustainability of a chain of business partners. In addition, the proposed mathematical model is applied to two case studies; one in the manufacturing sector and the other in the banking sector.

Resource utilisation Efficiency: A South African Provincial Evaluation

AbstractThe objective of this paper is to analyse the utilisation of production capacity and total under‐utilisation in order to identify weak‐performing industries across the nine South African provinces. Detecting inefficiencies within the different provinces will help to identify where sound managerial or government intervention is required, which can contribute to the future success of the New Growth Path Framework and the Strategic Integrated Projects. Using a multistage data envelopment analysis model at the subnational level, several categories of production factors are explored: intermediate demand, labour, capital, as well as taxes and subsidies. The results emphasise South Africa's weak infrastructure and the failure to effectively promote stability in managing factor inputs. The results further illustrate that industry scale efficiency for water and electricity are poorest across all provinces, highlighting the current water and energy supply concerns in South Africa and problem areas associated with the National Development Program.

An analysis of the implementation of energy efficiency measures in the vegetable oil industry of Iran: a data envelopment analysis approach

The vegetable oil industry is considered as one of the major industries contributing to energy consumption in Iran. Despite the increasing need to improve energy efficiency in this industry, previous studies show that energy-efficient technologies have not been applied in most plants and other energy efficiency measures have not yet been adopted. Accordingly, this paper addresses the implementation of energy efficiency measures in the vegetable oil industry. Using a data envelopment analysis (DEA), the relative efficiency of plants in the vegetable oil industry is compared at different stages of the implementation of energy efficiency measures. The most effective indices for improving energy efficiency were identified and a model was designed to implement energy efficiency measures in industrial plants. In the model, the implementation process consisted of 5 stages, each of which had its own inputs and outputs. A multi-stage DEA model was employed to evaluate the performance of vegetable oil plants at each individual stage as well as the aggregate efficiency of each plant. After estimating the total efficiency of all plants and evaluating performance at the individual stages for each plant, the plants with ideal conditions for implementing energy efficiency measures were identified. These plants can serve as a benchmark for other plants. Estimation of the average efficiency across plants at each stage indicated that the plants suffered from poor performance in the first and fourth stages. Therefore, the results of this study indicate a need to develop new strategies for improving energy efficiency at these two stages.

Risk-adjusted efficiency of the insurance industry: evidence from China

In order to investigate the interrelationship between risk and efficiency, based on the multistage data envelopment analysis (DEA) model, this paper introduces a modified measure of risk-adjusted efficiency for the insurance industry in China from 1999 to 2006. By comparing the results from the traditional DEA model and multistage DEA model, it is evident that there are significant changes in the firms' efficiency scores and their related ranks. The results show that the efficiency scores of the insurance firms studied tend to be underestimated if the endogenous risk factors due to bad management are not considered. With the continued development of the insurance industry in China, the insurance firms' capacity to manage risk has shown to have a significant positive impact on the improvement of their efficiency. Further, the risk-adjusted efficiency advantage of non-state-owned enterprises over state-owned enterprises is not as significant as it is when using the unadjusted models. However, the efficiency gap between foreign and domestic insurance firms shows an increasing trend during the sample period.

Measuring air routes performance using a fractional network data envelopment analysis model

This paper aims to propose a unified framework of data envelopment analysis (DEA) model so as to facilitate legitimate comparisons of performance among the production and service processes as well as overall operations. The fractional measure network DEA (FNDEA) model is constructed by analytically stratifying the structure of an operational network according to the transport service characteristics of air routes. We compare the proposed model with separate multi-stage DEA evaluation results by using an actual data set from the domestic air routes of an airline in Taiwan. The results show that the FNDEA model is significantly different from the separate multi-stage DEA model in magnitude of performance scores. Managerial strategies for the improvement of performance for the airline are also suggested.