Designing a knowledge-based system for benchmarking: A DEA approach

(1)

Designing a knowledge-based system for benchmarking: A DEA approach

Mei-Chi Lai

a

, Hao-Chen Huang

b,⇑

, Wei-Kang Wang

c

a

Institute of Health Policy and Management, National Taiwan University, Taiwan, ROC

b

Graduate Institute of Finance, Economics, and Business Decision, National Kaohsiung University of Applied Sciences, No. 415, Chien Kung Road, Kaohsiung 807, Taiwan, ROC

c

College of Management, Yuan Ze University, Taiwan, ROC

a r t i c l e

i n f o

Article history: Received 21 March 2010

Received in revised form 20 January 2011 Accepted 9 February 2011

Available online 13 February 2011 Keywords:

Benchmarking

Data envelopment analysis Hospital

Knowledge-based systems Performance evaluation Process benchmarking

a b s t r a c t

First developed by Xerox in 1979, benchmarking provides measurement and comparison to improve pro-cesses and achieve higher performance. Benchmarking has proven a powerful tool for total quality man-agement and process improvement. Successful benchmarking implementation is based on an effective benchmarking tool. To effectively implement benchmarking processes, this work proposes an integrated framework for the benchmarking tool and knowledge-based system using the data envelopment analysis (DEA) method, and then develops an intellectual benchmarking knowledge-based system (BKBS) for benchmarking, performance evaluation and process improvement. Accordingly, this work illustrates how the benchmarking knowledge-based system (BKBS) is implemented in a medical center. This system can help determine the particular benchmarking partners to evaluate the relative efﬁciency and ﬁll the gaps between the benchmarking partners in the healthcare industry. Finally, the intellectual benchmark-ing knowledge-based system offers a very fast way to implement the benchmarkbenchmark-ing processes.

1. Introduction

Academicians and researchers involved in strategic manage-ment have devoted increasing attention in the recent decade to the influence of benchmarking processes on process improvement, quality assurance, performance evaluation, and performance enhancement. Benchmarking has been defined as the search for companies’ or industry’s best practices that will lead to superior performance or organizational success. Since its initial develop-ment by Xerox in 1979, benchmarking as a total quality manage-ment tool has been widely adopted by manufacturing and service industries, and other industries around the world[6]. For example, Elmuti et al.[16]suggest that the benchmarking reasons and ben-efits involve performance assessment, continuous improvement, enhanced performance, enhanced learning, growth potential, job satisfaction, and total quality management. Consequently, bench-marking has been shown to influence organizational competitive advantage and success in a number of ways.

The process benchmarking and improvement are a virtual necessity for manufacturing and business activities. Because of the complexity and importance of continuous improvement or benchmarking activities, the benchmarking processes, DEA tech-nique, and knowledge-based system (KBS) are frequently used as the tools in support of benchmarking implementation or deci-sion-making. To effectively implement benchmarking, adequate

benchmarking tools, system, and IT support are needed. For exam-ple, knowledge-based systems (KBS) are computer-based tools that help managerial decision-making by presenting various effective alternatives. By the 1990s, intelligent knowledge-based systems had been playing an important role in new decision support tools. Consequently, numerous studies about KBS with benchmarking have been done, such as[21,51,32,37,30,42]. But there have been few studies done about the combined the benchmarking tool, KBS and DEA technique. Thus, in this study, an intelligent knowl-edge-based system is developed to provide benchmarking and improvement from the DEA technique. The KBS can be used as a benchmarking tool to improve the operations and process based decision-making information. The objective of KBS is to offer con-clusive references helping the decision maker to make correct deci-sions under complex situation and information. Consequently, the fundamental objective of intelligent benchmarking knowledge-based system (BKBS) is to develop a system and process for imple-menting benchmarking process to support needs in this work.

Based on the prior literature, this work has two related aims: (a) to propose an integrated framework for the benchmarking tool and knowledge-based system using the data envelopment analysis (DEA) method; and (b) to develop an intellectual benchmarking knowledge-based system for performance evaluation, benchmark-ing process and continuous improvement. By usbenchmark-ing the DEA meth-od as the analytical tool, this work attempted to answer the following related questions: (1) how can management improve efﬁciency and process with the benchmarking tool? (2) how can IT technique support the benchmarking processes and improve the organization performance? This work illustrates how the

⇑Corresponding author. Tel.: +886 7 3814526; fax: +886 7 3836380.

E-mail addresses:d94843004@ntu.edu.tw(M.-C. Lai),haochen@cc.kuas.edu.tw

(H.-C. Huang),jameswang@saturn.yzu.edu.tw(W.-K. Wang).

Contents lists available atScienceDirect

Knowledge-Based Systems

(2)

benchmarking knowledge-based system (BKBS) is implemented in a medical center. Accordingly, this work presents the use of the DEA to evaluate all of the benchmarking partners in DEA models in the healthcare industry.

The rest of the work is organized as follows. Section2presents a brief review of the knowledge-based system (KBS) and related applications. Section3presents a brief review of the benchmarking and related research. Section4describes the DEA theorem and re-lated research. Sections 5 and 6 describe the architecture of bench-marking knowledge-based system and the integration points of benchmarking and KBS. Section7presents an illustrative example in the healthcare industry. Finally, some concluding remarks and a summary are given in Section8.

2. The components of knowledge-based system and related applications

Knowledge-based system (KBS) is a computer application that analyzes business data and presents this data to help facilities user decision making. A KBS may present information graphically and may include either an expert system or artificial intelligence (AI). A KBS may be aimed at business executives or some other group of knowledge workers. KBS are a specific class of computerized information system that supports business and organizational decision-making. A properly designed KBS is an interactive soft-ware-based system designed to help decision makers compile use-ful information from raw data, documents, personal knowledge, and/or business models for problem solving and decision making. The Computer User High-Tech Dictionary defines a knowledge-based system (KBS) as a computer system designed to imitate hu-man problem-solving via a combination of artificial intelligence and a database of subject specific knowledge. Knowledge-based systems are based on artificial intelligence (AI) methods and tech-niques. The core components of knowledge-based systems are knowledge base and inference/reasoning mechanisms. KBS, like problem processing systems, function to retrieve information from a knowledge system and to use this information to derive useful results and for decision-making. KBS are computer systems that represent knowledge in the form of heuristics for problem solving to assist humans in decision-making[12]. In practice, KBS is a fre-quent abbreviation for knowledge-based systems.

In the literature on KBS, Dhaliwal and Benbasat [15] suggest that the four main components of KBS are generally as follows: knowledge base, inference engine, knowledge engineering tool, and speciﬁc user interface. Then, Chau and Albermani[8]propose that KBS comprise three basic components: knowledge base, con-text and inference mechanism. The knowledge base thus is the heart or core component of the KBS and contains domain expert knowledge stored via a variety of representation techniques (for example semantic networks, frames and logic) [14]; the most widely used technique or method is the ‘‘if (condition) then (ac-tion)’’ production rule.

Since the 1990s academics and researchers have recognized the importance of KBS and its related concepts became one of the most popular topics related to decision support tools or management information systems (MIS). Since its development KBS has been widely applied to various studies and issues, including perfor-mance assessment[57,59,56], e-procurement exception manage-ment [36], stock market investment [9], product pricing [48], dynamic logistics process management[11], marketing decision

[61], outsource manufacturing[10], urban infrastructure manage-ment[45], cost estimating[40], bank loan risk management[60], airborne decision support[23], strategic planning [24], work-re-lated risk analysis[43], debris-ﬂow problems analysis [55], and production [44]. Consequently, the KBS has gained considerable

acceptance recently in the current information management literature.

3. Benchmarking

3.1. The concept of the benchmarking

Benchmarking is ‘‘a process of measuring and comparing to identify ways to improve processes and achieve higher perfor-mance’’[27]. Xerox Corporation ﬁrst adopts benchmarking in the late 1970s. Since then, managers in different industries have used it to evaluate and improve the quality of their products, as well as work processes and work procedures. Benchmarking is a very ver-satile tool that can be applied in a variety of ways to meet a range of requirements for improvement. Benchmarking allows an organi-zation to objectively and thoroughly evaluate its processes to see if and how they can be improved[28].

Juran[26] suggests that a benchmark is a point of reference from which measurements and comparisons of any sort may be made. Elmuti et al.[16]divide the benchmarking types into four different types, including internal benchmarking, competitive benchmarking, functional or industry benchmarking, and process or generic benchmarking. Process benchmarking is used when the focus is on improving speciﬁc critical processes and operations. Benchmarking partners are sought from the best practice organiza-tions that perform similar work or deliver similar services. Process benchmarking invariably involves producing process maps to facil-itate comparison and analysis. This type of benchmarking can re-sult in beneﬁts in the short term.

Benchmarking is the practice of being humble enough to admit that someone else is better at something, and being wise enough to learn how to match and even surpass them at it. For some companies and organizations, benchmarking is synonymous with survival. It provides them with a way to assess their business per-formance. Through benchmarking, they gain a better understand-ing of their relative position in their industry. Benchmarkunderstand-ing works because it helps them to understand their own processes and enables them to learn from others.

Benchmarking also equals innovation. Real innovation comes from looking for the best examples outside one’s industry. This en-ables one to learn from other companies and achieve quantum leaps in performance that otherwise might take years to achieve. The purpose of a benchmarking process model is to describe the steps that should be performed when conducting a benchmarking study[58]. Consequently, numerous studies about benchmarking processes have been done, such as[50,62,1–3,22,19].

In those descriptions of benchmarking process, Spendolini[50]

divides the benchmarking process into five phases: (1) determine what to benchmark; (2) form a benchmarking team; (3) identify benchmarking partners; (4) collect and analyze benchmarking information; and (5) take action. Young[62]identifies four steps in the benchmarking process: (1) planning; (2) analysis; (3) inte-gration; and (4) action. Anderson and Pettersen [2]identify five distinct phases: (1) planning; (2) searching; (3) observation; (4) analysis; and (5) adaptation. Atkin and Brooks [3]identifies the benchmarking steps: (1) identify the subject of the exercise; (2) de-cide what to measure; (3) identify who to benchmark both within your sector and outside; (4) collect information and data; (5) ana-lyze findings and determine gap; (6) set goals for improvement; (7) implement new order; and (8) monitor the process of improve-ment. Hacker and Kleiner[22]propose 12 steps to avoid dysfunc-tional practices and improve benchmarking. The 12 steps are: (1) determine what to benchmark; (2) identify key performance indi-cators; (3) identify benchmarking partners; (4) determine the data collection method; (5) collect data; (6) understand performance

(3)

gaps; (7) predict future performance levels; (8) communicate ﬁnd-ings and gain acceptance; (9) establish functional goals and imple-mentation plans; (10) implement and monitor progress; (11) measure results against stakeholder wants and needs; (12) recali-brate benchmarks. Gohlke[19]uses a library benchmarking model to improve the performance of public libraries. It includes ﬁve steps: (1) conducting a preliminary analysis; (2) developing pro-cess measures; (3) identifying partners; (4) collecting and analyz-ing data; and (5) presentanalyz-ing results to management.

Nevertheless, a benchmarking wheel is a benchmarking process model that synthesizes advantages of a large number of existing benchmarking models[1]. Therefore, the author focuses on a study using the benchmarking wheel to study the benchmarking process. A benchmarking wheel, as Anderson [1] presents, is shown in

Fig. 1. The benchmarking processes are described as follows: Step 1 Plan:

(1) Determine the process to benchmark based on the organiza-tion’s critical success factors.

(2) Understand and document the process. (3) Measure the performance of the process.

Step 2 Find:

(4) Identify benchmarking partners. Step 3 Collect:

(5) Understand and document the benchmarking partners’ per-formance and practice.

Step 4 Analyze:

(6) Identify gaps in performance and the root causes of the gaps. Step 5 Improve:

(7) Plan the implementation of improvements.

(8) Implement improvements and monitor the implementation progress.

The planning stage is a preparatory phase, which provides a foundation for the ensuing study. The ﬁnding stage is often the most challenging phase of the entire study. The collecting stage is where the best practice processes of the benchmarking partners are observed and documented in much the same way as the com-pany’s own process was documented in the planning phase. In the analysis stage, the process knowledge from the planning and col-lecting stages is put together to identify the gaps in performance between the benchmarking partners and the causes for the gaps. The ﬁnal improvement stage can often be lengthy in duration com-pared with the previous four phases.

3.2. Benchmarking and KBS

Benchmarking is originally deﬁned and designed as a total qual-ity tool to facilitate the improvement of business operations and organizational performance. Gunasekaran [20] suggests that IT can be used to develop a benchmarking tool, and IT-enabled

benchmarking systems should provide immediate feedback and di-rectly involve participants in the data collection process and en-sure the quality and acceptance of study results. To date, a considerable number of researches have employed and combined the benchmarking concept and tool with the KBS studies, for exam-ple:[21,51,32,31,37,30,42].

Research by academicians St-Pierre and Delisle[51]present a fully implemented expert diagnostic system which evaluates on a benchmarking basis the performance of small- and medium-sized enterprise (SMEs), and highlight the development and use of a benchmarking-based ‘‘360-degrees’’ performance evaluation sys-tem for SMEs. Lau et al.[32]propose system encompasses hybrid artificial intelligence (AI) technologies, online analytical processing (OLAP) applications and neural networks and proposed a knowl-edge-based system that offers expandability and flexibility to al-low users to add more related factors for analysis to enhance the quality of decision making. Lau et al.[31]propose a virtual case-based benchmarking system (VCBS) which incorporates computa-tional intelligence technologies into partners’ benchmarking pro-cess to support decision-making. The proposed system consists of three main modules: data repository module, OLAP module and case-based reasoning (CBR) module. Marti[37]proposes strategic knowledge benchmarking system (SKBS) to refine the classic stra-tegic SWOT analysis. Lau et al.[30]propose a partners benchmark-ing assessment system (PBAS) which incorporates computational intelligence technologies into partners’ benchmarking process to support decision making. Naylor et al.[42]describe the knowledge acquisition methodology and the knowledge management meth-odology adopted for the development of a knowledge-based sys-tem to estimate the cash cost performance of the product delivery process of steel plants.

4. Data envelopment analysis

4.1. Data envelopment analysis (DEA) method

Farrell [17] introduces a framework for efficiency evaluation and measurement, which is subsequently studied by Charnes et al.[7], Banker et al.[5], etc. The development of linear program-ming approach is known as DEA. The DEA model assumes that the random error is zero so that all unexplained variations can be trea-ted as reflecting inefficiencies. The linear programming approach is flexible. It can measure input or output efficiency under the assumption of various types of constant returns to scale (CRS) and variable returns to scale (VRS). DEA is a non-parametric linear programming technique used to compare input and output data of production units, or decision marking units (DMUs), with input and output data of other similar DMUs. It is a technique used to measure and evaluate the relative performance of production units. DEA is commonly used to evaluate the efficiency of a number of producers. A typical statistical approach is characterized as a central tendency approach and it evaluates producers relative to an average producer. In contrast, DEA is an extreme point method and compares each producer with only the ‘‘best’’ producers.

The development of DEA methodology stems from the usual measure of productivity, a ratio of outputs to inputs. The formula-tion of a relative efﬁciency measure, or the ratio of weighted out-puts to weighted inout-puts, was introduced to account for the existence of multiple inputs and multiple outputs.Fig. 2 shows the procedure for DEA model[18].

4.2. DEA and process benchmarking

Data envelopment analysis (DEA) is suggested to aid traditional benchmarking activities and to provide guidance to management 1.Plan

2.Find

3.Collect 4.Analyze

5.Improve

(4)

8.2. Implications and future research

Several practical implications can be drawn from this investiga-tion. Benchmarking has demonstrated to be a powerful tool for improvement and total quality management. Management thus should make an effort to learn how to practically apply the inte-grated BKBS to achieve organizational competitive advantages and effective benchmarking. This work concludes that administra-tors of medical center can use this analysis to help them identify and manage benchmarking processes when adopting the BKBS. Several recommendations for future work and research could help to explore the BKBS, not only the concept of the architecture of BKBS, but also its usefulness in the practice.

First, in recent years, fuzzy rule-based systems (FRBS), case-based reasoning (CBR) and model-case-based reasoning (MBR) have emerged as important and complementary reasoning methodolo-gies for application to decision support systems. For complex problem solving, it is useful to integrate FRBS, CBR and MBR in decision-making. In the future, BKBS should integrate RBR, CBR and MBR for benchmarking implementation, performance assess-ment, and process improvement.

Second, during the past decade academicians and researchers have devoted increasing attention to the impact of management tools on strategic performance improvement, such balanced score-card (BSC), Activity-based Costing/Management (ABC/M), Target Costing, Six Sigma, etc. In the future, the BKBS should integrate those management tools for process benchmarking.

Finally, it is recommended that the approach outlined in this work be replicated in other industries and companies. Future re-search works will focus on validating the proposed BKBS and asso-ciated strategic objectives and performance measures, as well as on implementing the BKBS to the other companies or organization to test the effectiveness of this BKBS for process benchmarking. References

[1] B. Anderson, The Results of Benchmarking and a Benchmarking Process Model, Ph.D. Dissertation, Norwegian Institute of Technology, Trondheim, Berlin, 1995.

[2] B. Anderson, P. Pettersen, The Benchmarking Handbook, Chapman and Hall, London,, 1996. pp. 13–15.

[3] B. Atkin, A. Brooks, Total Facility Management, Blackwell Science, Oxford, 2000. pp. 132–134.

[4] A.D. Athanassopoulos, Decision support for target-based resource allocation of public services in multiunit and multilevel systems, Management Science 44 (2) (1998) 173–187.

[5] R.D. Banker, A. Charnes, W.W. Cooper, Some models for estimating technical and scale inefﬁciencies in data envelopment analysis, Management Science 30 (9) (1984) 1078–1092.

[6] R.C. Camp, Benchmarking: The Search for the Industry Best Practice that Leads to Superior Performance, ASQC Quality Press, Milkwaukee, WI, 1989. [7] A. Charnes, W.W. Cooper, E. Rhodes, Measuring the efﬁciency of decision

making units, European Journal of Operational Research 2 (1) (1978) 95–112. [8] K.W. Chau, F. Albermani, Expert system application of preliminary design of water retaining structures, Expert Systems with Applications 22 (2) (2002) 169–178.

[9] V. Cho, MISMIS – a comprehensive decision support system for stock market investment, Knowledge-Based Systems 23 (6) (2010) 26–633.

[10] K.L. Choy, W.B. Lee, H.C.W. Lau, L.C. Choy, A Knowledge-based Supplier Intelligence Retrieval System for Outsource Manufacturing, Knowledge-Based Systems 18 (1) (2005) 1–17.

[11] H.K.H. Chow, K.L. Choy, W.B. Lee, A dynamic logistics process knowledge-based system – an RFID multi-agent approach, Knowledge-Based Systems 20 (4) (2007) 357–372.

[12] J.A. Clark, F. Soliman, A graphical method for assessing knowledge-based systems investments, Logistics Information Management 12 (1/2) (1999) 63– 77.

[13] N. Donthu, E.K. Hershberger, T. Osmonbekov, Benchmarking marketing productivity using data envelopment analysis, Journal of Business Research 58 (11) (2005) 1474–1482.

[14] G. Curtis, D. Cobham, Business Information Systems: Analysis, Design and Practice, Pearson Education Limited, Harlow, 2002.

[15] J.S. Dhaliwal, I. Benbasat, The use and effects of knowledge-based system explanations: theoretical foundations and a framework for empirical evaluation, Information Systems Research 7 (1996) 342–362.

[16] D. Elmuti, Y. Kathawala, S. Lloyed, The benchmarking process: assessing its value and limitations, Industrial Management 39 (4) (1997) 12–19. [17] M.J. Farrell, The measurement of productive efﬁciency, Journal of the Royal

Statistical Society Series A. General 120 (3) (1957) 253–281.

[18] B. Golany, Y. Roll, An application procedure for DEA, OMEGA: International Journal of Management Science 17 (1989) 237–250.

[19] A. Gohlke, Benchmarking for strategic performance improvement: using a total quality management tool, in: 2001 Library workshop – library benchmarking, Library Benchmarking International, 2001.

[20] A. Gunasekaran, Benchmarking tools and practices for twenty-ﬁrst century competitiveness, Benchmarking 8 (2) (2001) 86–87.

[21] Y.B. Guo, A. Qasem, Z.X. Pan, J. Heﬂin, A requirements driven framework for benchmarking semantic web knowledge based systems, IEEE Transactions on Knowledge and Data Engineering 19 (2) (2007) 297–309.

[22] M.E. Hacker, B.M. Kleiner, 12 Steps to better benchmarking, Industrial Management 42 (2) (2000) 20–23.

[23] H. Howells, A. Davies, B. Macauley, R. Zancanato, Large scale knowledge based systems for airborne decision support, Knowledge-Based Systems 12 (5–6) (1999) 215–222.

[24] H.C. Huang, Designing a knowledge-based system for strategic planning: a balanced scorecard perspective, Expert Systems with Applications 36 (1) (2009) 209–218.

[25] T.L. Ju, Representing organizational memory for computer-aided utilization, Journal of Information Science 32 (5) (2006) 420–433.

[26] J.M. Juran, Benchmarking for World Class Leadership, Participant Guide, Juran Institute, New York, NY, 1994.

[27] P. Keehley, S. Medlin, S. MacBride, L. Longmire, Benchmarking for Best Practices in the Public Sector, Jossey Bass, California, 1997.

[28] J.J. Kline, Activity-based costing and benchmarking: a tandem for quality-oriented governments, Journal of Government Financial Management 52 (3) (2003) 50–54.

[29] H.C.W. Lau, K.L. Choy, P.K.H. Lau, W.T. Tsui, L.C. Choy, An intelligent logistics support system for enhancing the airfreight forwarding business, Expert Systems 21 (5) (2004) 253–268.

[30] H.C.W. Lau, W.B. Lee, P.K.H. Lau, Development of an intelligent decision support system for benchmarking assessment of business partners, Benchmarking 8 (5) (2001) 376–395.

[31] H.C.W. Lau, P.K.H. Lau, R.Y.K. Fung, F.T.S. Chan, F.T.S. R.W.L. Ip, A virtual case benchmarking scheme for vendors’ performance assessment, Benchmarking 12 (1) (2005) 61–80.

[32] H.C.W. Lau, A. Ning, K.F. Pun, K.S. Chin, W.H. Ip, A knowledge-based system to support procurement decision, Journal of Knowledge Management 9 (1) (2005) 87–100.

[33] S.H. Liao, A knowledge-based architecture for implementing Military Geographical Intelligence System on Intranet, Expert Systems with Applications 20 (4) (2001) 313–324.

[34] S.H. Liao, An intranet-based architecture for Building Military Scenario Training Systems, Journal of the Operational Research Society 56 (5) (2005) 504–513.

[35] J.D. Linton, J. Morabito, J.S. Yeomans, An extension to a DEA support system used for assessing R&D projects, R&D Management 37 (1) (2007) 29–36. [36] Q. Liu, S.X. Sun, H. Wang, J. Zhao, A multi-agent based system for

E-procurement exception management, Knowledge-Based Systems 24 (1) (2011) 49–57.

[37] J.M.V. Marti, Strategic knowledge benchmarking system (SKBS): a knowledge-based strategic management information system for ﬁrms, Journal of Knowledge Management 8 (6) (2004) 31–49.

[38] J.C. Martín, C. Román, A benchmarking analysis of spanish commercial airports: A comparison between SMOP and DEA ranking methods, Networks & Spatial Economics 6 (2) (2006) 111–134.

[39] H. Min, S.J. Joo, Benchmarking the operational efﬁciency of third party logistics providers using data envelopment analysis, Supply Chain Management 11 (3) (2006) 259–265.

[40] A. Mohamed, T. Celik, Knowledge based-system for alternative design, cost estimating and scheduling, Knowledge-Based Systems 15 (3) (2002) 177–188. [41] R. Narasimhan, S. Talluri, J. Sarkis, A. Ross, Efﬁcient service location design in government services: a decision support system framework, Journal of Operations Management 23 (2) (2007) 163–178.

[42] J.B. Naylor, J. Grifﬁths, M.M. Naim, Knowledge-based system for estimating steel plant performance, International Journal of Operations & Production Management 21 (7) (2001) 1000–1019.

[43] T. Padma, P. Balasubramanie, Knowledge based decision support system to assist work-related risk analysis in musculoskeletal disorder, Knowledge-Based Systems 22 (1) (2009) 72–78.

[44] M. Pan, Y. Rao, An integrated knowledge based system for sheet metal cutting – punching combination processing, Knowledge-Based Systems 22 (5) (2009) 368–375.

[45] A. Quintero, S. Pierre, A knowledge-based approach for managing urban infrastructures, Knowledge-Based Systems 15 (8) (2002) 449–463.

[46] T. Sedbrook, Integrating E-business XML business forms and rule-based agent technologies, Expert Systems 18 (5) (2001) 250–265.

[47] H. Seol, J. Choi, G. Park, Y. Park, A framework for benchmarking service process using data envelopment analysis and decision tree, Expert Systems with Applications 32 (2) (2007) 432–440.

[48] S. Shakya, C.M. Chin, G. Owusu, An AI-based system for pricing diverse products and services, Knowledge-Based Systems 23 (4) (2010) 357–362.

(5)

[49] H.D. Sherman, J. Zhu, Benchmarking with quality-adjusted DEA (Q-DEA) to seek lower-cost high-quality service: evidence from a US bank application, Annals of Operations Research 145 (2006) 301–319.

[50] M. Spendolini, The Benchmarking Book, American Benchmarking Association, New York, NY, 1992.

[51] J. St-Pierre, S. Delisle, An expert diagnosis system for the benchmarking of SMEs’ performance, Benchmarking 13 (1/2) (2006) 106–119.

[52] S. Su, M.C. Lai, H.C. Huang, Healthcare industry value creation and productivity measurement in an emerging economy, Service Industries Journal 29 (7) (2009) 963–975.

[53] Q. Tian, J. Ma, O. Liu, A hybrid knowledge and model system for R&D project selection, Expert Systems with Applications 23 (3) (2002) 265–271. [54] W.J. Verkooijen, Automated ﬁnancial diagnosis: a comparison with other

diagnostic domains, Journal of Information Science 19 (2) (1993) 125–135. [55] S. Wan, T.C. Lei, A knowledge-based decision support system to analyze the

Debris-ﬂow problems at Chen-Yu-Lan River, Taiwan, Knowledge-Based Systems 22 (8) (2009) 580–588.

[56] W.K. Wang, A knowledge-based decision support system for measuring the performance of Government Real Estate Investment, Expert Systems with Applications 29 (4) (2005) 901–912.

[57] W.K. Wang, H.C. Huang, M.C. Lai, Design of a knowledge-based performance evaluation system: a case of high-tech state-owned enterprises in an emerging economy, Expert Systems with Applications 34 (3) (2008) 1795–1803. [58] G.H. Watson, Strategic Benchmarking: How to Rate Your Company’s

Performance against the World’s Best, John Wiley & Sons, New York, USA, 1993.

[59] W. Wen, Y.H. Chen, I.C. Chen, A knowledge-based decision support system for measuring enterprise performance, Knowledge-Based Systems 21 (2) (2008) 148–163.

[60] B. Yang, L.X. Li, Q. Xie, J. Xu, Development of a KBS for managing bank loan risk, Knowledge-Based Systems 14 (5–6) (2001) 299–302.

[61] U. Yavuz, A.S. Hasiloglu, M.D. Kaya, R. Karcioglu, S. Ersoz, Developing a marketing decision model using a knowledge-based system, Knowledge-Based Systems 18 (2–3) (2005) 125–129.

[62] S. Young, Checking performance with competitive benchmarking, Professional Engineering 6 (2) (1993) 14–15.