Desheng Wu

Using DEA-neural network approach to evaluate branch efficiency of a large Canadian bank

Abstract In todays economy and society, the banking industry is of great importance to every one of us. We all depend on the efficiency and quality of services that the banking industry provides. With the improvement in technology, the competition in the banking industry has become increasingly intense. Therefore, performance analyses in the banking industry attract more and more attention. This paper integrates data envelopment analysis (DEA) and neural networks (NNs) to examine the relative branch efficiency of a big Canadian bank. The results are compared with the normal DEA results. On the whole they are comparable. Furthermore, the guidance on how to improve the branch performance is given. Neural networks are also applied to do short-term efficiency prediction. Finally, the comparison between these two approaches is presented.

The method of grey related analysis to multiple attribute decision making problems with interval numbers

Multiple attribute decision making is important in many decision making contexts where tradeoffs are involved. The use of qualitative input has proven especially attractive, allowing subjective inputs to be used. However, such systems inherently involve uncertainty with respect to parameter inputs, especially when multiple decision makers are involved. This paper presents the method of grey related analysis to this problem, using interval fuzzy numbers. The method standardizes inputs through norms of interval number vectors. Interval valued indexes are used to apply multiplicative operations over interval numbers. The method is demonstrated on a practical problem.

Supplier selection: A hybrid model using DEA, decision tree and neural network

As the most important responsibility of purchasing management, the problem of vendor evaluation and selection has always received a great deal of attention from practitioners and researchers. This management decision is a challenge due to the complexity and various criteria involved. This paper presents a hybrid model using data envelopment analysis (DEA), decision trees (DT) and neural networks (NNs) to assess supplier performance. The model consists of two modules: Module 1 applies DEA and classifies suppliers into efficient and inefficient clusters based on the resulting efficiency scores. Module 2 utilizes firm performance-related data to train DT, NNs model and apply the trained decision tree model to new suppliers. Our results yield a favorable classification and prediction accuracy rate.

Simulation of fuzzy multiattribute models for grey relationships

Multiattribute decision making involves tradeoffs among alternative performances over multiple attributes. The accuracy of performance measures are usually assumed to be accurate. Most multiattribute models also assume given values for the relative importance of weights for attributes. However, there is usually some uncertainty involved in both of these model inputs. Outranking multiattribute methods have always provided fuzzy input for performance scores. Many analysts have also recognized that weight estimates also involve some imprecision, either through individual decision maker uncertainty, or through aggregation of diverging group member preferences. Many fuzzy multiattribute models have been proposed, but they have focused on identifying the expected value solution (or extreme solutions). This paper demonstrates how simulation can be used to reflect fuzzy inputs, which allows more complete probabilistic interpretation of model results.

Efficiency analysis of cross-region bank branches using fuzzy data envelopment analysis

In today’s economy and society, performance analyses in the services industries attract more and more attention. The traditional data envelopment analysis (DEA) approach requires a consistent operating environment. However, in reality, there is a need to evaluate the units belonging to different environment. This reality challenges the traditional methods of applying DEA theory to real-world cases where benchmarking across region can be a very important undertaking. This paper introduces the fuzzy logic into DEA formulation to deal with the environmental variables so that the performance of bank branches from different regions can be assessed. The inner-province and inter-province comparison are given based on the fuzzy DEA results. These results are also compared with the results from traditional DEA analysis.

Risk management models for supply chain: a scenario analysis of outsourcing to China

Purpose – A key process involved in supply chains is a priori evaluation of potential partners, not only in terms of expected cost (which includes exchange rate risk), but also in terms of other risks. These risks can include product failure, producing company failure (such as bankruptcy), and even political risk. This paper aims to compare tools to aid supply chain organizations in measuring, evaluating, and assessing risk in this environment.Design/methodology/approach – The authors demonstrate the use of DEA, followed by a DEA simulation model and also a Monte Carlo simulation using a risk‐adjusted cost concept. Once non‐dominated partners are identified by DEA, simulation analysis is applied to compare expected performance of vendors, and the range of expected outcomes can be identified, aiding supply chain core organizations to better select producing partners.Findings – The authors consider strategies of outsourcing to China, as well as other nations under various forms of risk. A scenario analysis ...

A comparison of stochastic dominance and stochastic DEA for vendor evaluation

Vendor selection involves decisions balancing a number of conflicting criteria. Data envelopment analysis (DEA) is a mathematical programming approach capable of identifying non-dominated solutions, as well as assessing relative efficiency of dominated solutions. A simple multi-attribute utility function can be applied to a small set of alternatives, providing a tool to assess relative value, but is subject to error if estimated measures are not precise. This paper compares stochastic DEA with a multiple-criteria model in a vendor selection model involving multiple criteria, reporting simulation experiments varying the degree of uncertainty involved in model parameters.

An application of pattern recognition on scoring Chinese corporations financial conditions based on backpropagation neural network

The paper follows three parts on the whole. The first part reviews the literature on financial diagnosis and the appropriate measures to be currently used. Thus the research gaps in the fields are highlighted. Next part details the variables and samples selection, data, analysis and results applying to scoring financial conditions of a Chinese corporation. By using pattern recognition theory, a scoring model is developed to analyze corporate financial conditions by backpropagation neural networks. It has been proved to be better than ordinary BPNN and traditional multivariate discriminant analysis. Finally, conclusions are presented.

A note on DEA efficiency assessment using ideal point: An improvement of Wang and Luo’s model

Abstract Evaluating the efficiency of organizational units continues to be a difficult problem to solve, especially when the multiplicity of inputs (resources, costs) and outputs (services, products) associated with these units is considered. This paper considers a previous article published by Wang and Luo [Y. Wang, Y. Luo, DEA efficiency assessment using ideal and anti-ideal decision-making units, Applied Mathematics and Computation 173 (2) (2006) 902–915] in the journal of Applied Mathematics and Computation where data envelopment analysis (DEA) and the technique for order preference by similarity to ideal solution (TOPSIS) are integrated in ranking of decision-making units (DMUs). Wang and Luo (2006) contribute to a very interesting topic by showing that the TOPSIS idea can be combined to DEA for a comprehensive ranking of DMUs. However, this paper finds that their approach is problematic in employing the negative ideal point (NIP) for DEA computation. Their ideal point based models rely on using conflicting efficiency concepts. We slightly revised the models so that a DEA analysis using TOPSIS idea can be performed. Numerical demonstration reveals that our approach produces a ranking result that is consistent with that in previous studies.

Simultaneous analysis of production and investment performance of Canadian life and health insurance companies using data envelopment analysis

Abstract A new data envelopment analysis (DEA) model is created to provide valuable managerial insights when assessing the dual impacts of operating and business strategies for Canadian life and health (L&H) insurance industry. This problem-oriented new DEA model can simultaneously assess the production and investment performance of insurers, differing from classical DEA models appropriate for independent performance evaluation. The mathematical solution is provided for this new model and the results show that the Canadian L&H insurance companies operated very efficiently for the examined 3-year period (1996–1998). In addition, no scale efficiency in the Canadian L&H insurance industry is found in this study.