Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

R&D Project selection by integrated grey analytic network process and grey relational analysis: an implementation for home appliances company

R&D Project selection by integrated grey analytic network process and grey relational analysis:... 10.7603/s40690-015-0014-8 JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 2015 VOLUME 8 NUMBER 2 (35-41) R&D PROJECT SELECTION BY INTEGRATED GREY ANALYTIC NETWORK PROCESS AND GREY RELATIONAL ANALYSIS: AN IMPLEMENTATION FOR HOME APPLIANCES COMPANY Umut R. TUZKAYA Ezgi YOLVER YTÜ, Industrial Engineering Department, YTÜ, Industrial Engineering Department, Barbaros BulvarÕ ,34349 YÕ ldÕ z-Beú iktaú / ø stanbul Barbaros BulvarÕ , 34349 YÕ ldÕ z-Beú iktaú / ø stanbul tuzkaya@yildiz.edu.tr eyolver@gmail.com th nd Received: 28 April 2015, Accepted: 02 July 2015 ABSTRACT For many firms, the key to improve competitiveness is their ability of research and development (R&D);therefore the R&D project selection is an essential decision process for them. In this study, we worked on R&D Project Selection issue and performed an implementation for a home appliances company. Wefirst discussed important criteria for R&D projects selection with R&D specialists in the company. Inorder to evaluate projects, many criteria, containing various sub-criteria were determined via extensiveliterature research. After reviewing multi criteria decision methods in order to handle theinterdependencies among the criteria and the sub-criteria, Analytic Network Process (ANP) was chosen.Due to being conformed to characteristics of R&D projects, the ANP model generated basing on greynumbers. Also, ANP was used to get the weight of criteria. The experts filled the pairwise comparisonmatrices, which were built up for defining the importance and influences of the criteria/sub-criteria inthe ANP model. According to these matrices, weights were determined. Then, determined alternativeprojects were ranked via Grey Relational Analysis (GRA) method. The model was applied on a real liferefrigerator projects in a home appliances company. Keywords: R&D Project Selection, Grey Analytic Network Process, Grey Relational Analysis. GRø ANALø Tø K Aö SÜRECø VE GRø ø L Kø SEL ANALø Z ø LE ENTEGRE EDø LMøù AR-GE PROJELERø Nø N SEÇø Mø : EV ALETLERø ùø RKETø NDE Bø R UYGULAMA ÖZET Araú tÕ rma ve geliú tirme yetene÷ i bir çok ú irketin rekabet etme gücünü arttÕ racak önemli bir faktördür. Bu nedenle Ar-Ge projelerinin seçimi ú irketler için temel karar sürecidir. Bu çalÕ ú mada, Ar-Ge projeleri seçimi üzerine çalÕ ú Õ lmÕ ú ve bir ev aletleri ú irketinde konuyla ilgili bir uygulama yapÕ lmÕ ú tÕ r. ø lk olarakAr-Ge uzmanlarÕ yla birlikte Ar-Ge projeleri seçiminde önemli olan kriterler üzerine çalÕ ú Õ lmÕ ú tÕ r. Projeleri de÷ erlendirmek için birçok kriter ve bunlara ba÷ lÕ alt kriterler geniú bir literatür araú tÕ rmasÕ yla belirlenmiú tir. Birçok çok kriterli karar verme metodu incelendikten sonra, kriterler ve kriterler arasÕ ba÷ lÕ lÕ ÷ Õ ele almak amacÕ yla ANP metodu kullanÕ lmÕ ú tÕ r. Bu çalÕ ú mada Ar-Ge projelerinin karakteriyle uyumlu olmasÕ nedeniyle gri sayÕ lara dayalÕ ANP modeli oluú turulmuú ve kriter a÷ Õ rlÕ klarÕ nÕ n belirlenmesi için kullanÕ lmÕ ú tÕ r. ANP modelinde kriterlerin ve alt kriterlerin birbirlerine olan etkileri ve önem derecelerinin belirlenmesi için ikili karú Õ laú tÕ rma matrisleri oluú turulmuú ve uzmanlar tarafÕ ndan de÷ erlendirilmiú tir. Oluú turulan bu matrislere göre a÷ Õ rlÕ klar belirlenip, tanÕ mlanan alternatif projelerGri ø liú kisel Analiz (Gø A) metodu kullanÕ larak sÕ ralanmÕ ú tÕ r. Uygulama olarak da bir ev aletleri ú irketindeki gerçek buzdolabÕ Ar-Ge projelerinde bu modele baú vurulmuú tur. Anahtar Kelimeler: Ar-Ge Projelerinin Seçimi, Gri Analitik A÷ Süreci, Gri ø liú kisel Analiz. * TUZKAYA, YOLVER Corresponding Author øù R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company right projects in order to survive in the competitive 1. INTRODUCTION environment. The projects that will lead to success R&D project management is one of the most difficult should have a positive cost/benefit, provide the areas in projects management. In today’s world, organization to improve the chance of success, have precondition of surviving of a company in highly futuristic scope and strategic fit on stakeholder competitive environment is conducting Research and involvement [2]. Development (R&D) projects. Developed countries generally encourage the R&D activities of private The selection of R&D project is a complex decision- sector and government to improve the overall making problem encountered by most industrial firms. competitive power of the country. R&D project selection requires consideration of uncertain and/or subjective multiple criteria. The Companies that want to maintain their existence in selecting and determining relative importance of competitive environment must continually change and criteria will differ according to the goals and develop their products, services and production objectives of the sponsoring organization and the processes. This is only possible through R&D nature of the R&D activity itself [3]. activities and innovation. R&D activities generally involve scientific and technological uncertainties. A wide range of criteria and sub-criteria such as Innovations are also unpredictable, and thus involve strategic fit, capacity, technical success, funding, risks, large uncertainties. Corporate R&D management, considerations, opportunity costs, manpower, etc., are supporting the maximal use of new innovations and used for decision process [2]. Obviously, wrong technologies, always tries to keep the company up decisions in project selection have two negative with the pace of technological development. R&D consequences: (1) resources are spent on unsuitable projects are tools for the company’s management to projects and, (2) the organization loses the benefits it outpace competitors and obtain new information about could have gained if these resources had been spent on promising technologies and methods. With such new more suitable projects [4]-[5]. Therefore, most information, companies aim to defend and build companies apply the scientific selection methods that sustainable competitive advantages [1]. are generally multi criteria decision methods for R&D projects. 2. R&D PROJECT SELECTION An extensive literature review is carried out on the Around the world advanced high-tech companies are subject of R&D Project selection and investing R&D projects. R&D projects must be evaluationcriteria. R&D project selection criteria compatible with the company’s vision and mission. available in the literature are categorized into five Such projects should provide benefits for stakeholders, factors; technical, marketing, financial, environmental link with the company’s expertise and have clear and organizational factors. In this study, 12 sub- objectives in place along with built-in appropriate criteria,which are evaluated by the decision evaluation resources and have prospects of sustaining committee, are classified into these five factors. The itself. The most challenging tasks areto choose the sub-criteria that are grouped are shown in Figure 1. R&D PROJECT SELECTION CRITERIA Technical Marketing Financial Environmental Organizational Factors Factors Factors Factors Factors Existence of Probability of Probability Cost of Environmental Technical Required of Market Development Consideration Facilities Success Success Fitting Safety Advancement Degree of Investment Organizational Consideration Technology Competition Strategy Product Cost Patentability Up Figure 1. Project selection criteria. TUZKAYA, YOLVER 36 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company 3.2. Grey AnalytÕ c Network Process (GANP) 3. MULTI CRITERIA DECISION MAKING METHODS GANP method is applied for weighting of criteria using ANP and grey system theory based on In this study, multi criteria decision-making methods Saaty’sANP model. The ANP is coupling of two parts. are used on selecting of R&D projects. These methods The first consists of a control hierarchy or network can provide solutions to increasing complex ofcriteria and sub-criteria that control the interactions. management problems. Here, the background The second is a network of influences among information about the used multi criteria decision theelements and clusters. The network varies from methods is provided. Firstly, Grey System approach is criterion to criterion and a different super matrix explained. Then, Grey Analytic Network Process oflimiting influence is computed for each control (GANP) method and finally Grey Relational Analysis criterion. Finally, each of these super matrices is (GRA) method are described. weightedby the priority of its control criterion and the results are synthesized through addition for all the 3.1. Grey System Theory controlcriteria [10]. Grey theory, which was proposed by Chinese scholar Professor Deng Julong [6], is one of the new Pairwise Comparison and Local Weights mathematical theories born out of the concept of the Estimation: The ANP is based on deriving ratio grey set. It is an effective method used to solve scalemeasurements founded on pairwise comparisons uncertainty problems with discrete data and to derive ratio scale priorities for the distribution incomplete information [7]. The concept of the Grey ofinfluence among the elements and clusters of the System, in its theory and successful application, is network [11]. In the study, grey numbers were now well known in China [8]. The major advantage of applied.The parameters G1 and G1, denote the grey theory is that it can handle both incomplete smallest possible value and the largest possible value information and unclear problems very precisely. It that describea fuzzy event. Grey number scale that serves as an analysis tool especially in cases where used in this study is given in Table 1. there is insufficient data [9]. Table 1. Linguistic scales for difficulty and Õ mportance [12]. Linguistic Scale For Importance Grey Number Scale Grey Number Reciprocal Scale Just equal (E) (1, 1) (1, 1) Equally important (EI) (1/2, 3/2) (2/3, 2) Weakly more important (WMI) (1, 2) (1/2 ,1) Strongly more important (SMI) (3/2, 5/2) (2/5, 2/3) Very strongly more important (VSMI) (2, 3) (1/3, 1/2) Absolutely more important (AMI) (5/2, 7/2) (2/7, 2/5) Pairwise comparison matrices are formed by the other element with which it interacts, the super matrix decision committee by using the grey number scale. is raised to limiting Powers [14]. Before taking the limitof the matrix, it must first be reduced to a column Super Matrix Formation and Analysis: According stochastic matrix (i.e. weighted super matrix), each to the ANP approach, we need to define ofwhose column sums to unity. Then via interdependencies among factors and clusters. This is normalization, the normalized weight vectors can be also possible with super matrix formation. The found in therelevant rows of the normalized limit relative weights are aggregated into a super matrix super matrix. In this way, global weights for all based upon influence from one cluster to another, or elements will beachieved. from one factor to another within a cluster itself. The super matrix formation incorporates four elements:(1) 3.3. Grey RelatÕ onal AnalysÕ s relationships to the final objective; (2) comparisons GRA method is applied for ranking of alternative among factors and clusters; (3) comparisons projects. GRA is a new analysis method, which ofalternative relationships with respect to the factors; hasbeen proposed in the Grey system theory and it is and (4) an identity matrix for all alternatives founded by Professor Deng Julong from Huazhong (unlessthe alternatives influence each other) [13]. University of Science and Technology, People’s Republic of China [15]. Calculate The Global Weight: Finally, to yield thecumulative influence of each element on every TUZKAYA, YOLVER 37 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company GRA is used to determine the relationship between selection criteria that are used in literature with two two series of data in a grey system. Its structure R&D specialists and then we determined the hasuncertainty, therefore it handles the problems convenient ones. Secondly, the ANP model formed by consisted of discrete data and partial information [16]. the criteria and sub-criteria determined in the first It operates the grey relational grade to determine the step. Criteria have been evaluated by two decision relational degree of factors. Grey relation analysis is makers via linguistic variables that can be expressed also an effective means of analyzing the relationship in grey number. Then, a degree of grey possibility is between sequences with less data and can analyze proposed to calculate the weights. Thirdly, alternative many factors that can overcome the disadvantages of projects have been evaluated by decision makers in statistical method [17]. GRA is based on geometrical the same way with GANP method’s weighting. mathematics, which compliance with the principles of Finally the GRA model formed and alternative normality, symmetry, entirety, and proximity. GRA is projects have been ranked. A detailed implementation suitable for solving complicated interrelationships steps are given below. between multiple factors and variables. There are 3 main steps in GRA [15]. The first step is data pre- 4.1. Data GatherÕ ng And UsÕ ng The Ganp processing, the second step is locating the grey Technique relational coefficient and the final step is calculating Firstly, main factors are evaluated by using pairwise of grey relational grade. comparison matrices (assumed that there is nodependence among the factors). The decision 4. IMPLEMENTATION committee has formed pairwise comparison matrices byusing the scale given in Table 1. Linguistic scale is We have performed an implementation about R&D placed in the relevant cell against the grey project selection issue for an R&D system numberwhile evaluating. Then this scale will be development department in a home appliances transformed into whitened value by the whitening company. Various projects on refrigerator production membershipfunction and local weights are calculated processes are considered for ranking. Some of these using GANP method formulation. projects have already been actualized and some of them have not been actualized. Objective of this study Pairwise comparison matrix for the main factors is is to rank the projects according to priority and to see filled and the local weights for the main factors whether the right projects have been actualized or arecalculated as shown in Table 2. not.Firstly, we have analyzed the R&D project Table 2. Local weights and pairwise comparison matrix of main factors. MAIN FACTORS Technical Marketing Financial Environmental Organizational Local Weight Technical (1, 1) (2/5, 2/3) (1/3, 1/2) (3/2, 5/2) (2/3, 2) 0,16 Marketing (3/2, 5/2) (1, 1) (2/5, 2/3) (2, 3) (3/2, 5/2) 0,24 Financial (2, 3) (3/2, 5/2) (1, 1) (5/2, 7/2) (2, 3) 0,35 Environmental (2/5, 2/3) (2/5, 2/3) (1/3, 1/2) (1, 1) (2/5, 2/3) 0,1 Organizational (1/2, 3/2) (2/5, 2/3) (1/3, 1/2) (3/2, 5/2) (1, 1) 0,15 Sub-factors are also evaluated and weighted in the calculated in Table 3. Sub-factors of other main same way with main factors. Pairwise factors are also evaluated and weighted in the same comparisonmatrix for sub-factors of technical factors way. is filled and the local weights for their sub-factors are Table 3. Local weights and pairwise comparison matrix of sub-factors of technical factor. Probability of Advancement TECHNICAL FACTORS Patentability Local Weights technical success technology Probability of technical success (1, 1) (2, 3) (3/2, 5/2) 0,511 Advancement technology (1/3, 1/2) (1, 1) (2/5, 2/3) 0,182 Patentability (2/5, 2/3) (3/2, 5/2) (1, 1) 0,307 Afterwards, interdependent weights of the main each factor on every other factor using pairwise factors are calculated and the dependencies among comparisons. Same linguistic variable scale is used themain factors are considered. Dependence among again. Allthe grey evaluation matrices are produced in the factors is determined by analyzing the impact of the same manner. Then this scale will be transformed TUZKAYA, YOLVER 38 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company intowhitened value by the whitening membership After pairwise comparisons for technical factors are function and local weights are calculated using GANP completed, the resulting relative importance weight method formulation. sare presented in Table 4. Table 4. The inner dependence matrix of the factors with respect to ‘‘Technical Factors”. Relative TECHNICAL Marketing Financial Environmental Organizational Importance FACTORS Weight Marketing (1, 1) (2/3, 2) (1, 2) (3/2, 5/2) 0,32 Financial (1/2, 3/2) (1, 1) (1, 2) (3/2, 5/2) 0,3 Environmental (1/2, 1) (1/2, 1) (1, 1) (1, 2) 0,22 Organizational (2/5, 2/3) (2/5, 2/3) (1/2, 1) (1, 1) 0,16 Same operations are generated for the sub-factors of dependence matrices are multiplied with the local each main factor and inner dependence relative weights of the factors. The result of the GANP, Table importance weights are obtained. Finally, to compute 5 is obtained. the interdependent weights of the factors, these inner Table 5. Computed weights. Main Criteria (Factors) Factors Local Weights Sub-Criteria (Sub-Factors) Local Weights Probability of technical success 0,511 Technical Factors 0,19 Advancement technology 0,182 Patentability 0,307 Probability of market success 0,414 Marketing Factors 0,2 Degree of competition 0,586 Cost of development 0,203 Financial factors 0,28 Investment 0,353 Product Cost Up 0,444 Environmental considerations 0,253 Environmental Factors 0,17 Safety considerations 0,747 Existence of required facilities 0,29 Organizational Factors 0,16 Fitting organizational strategy 0,71 4.2. Application of The Gra Technique Then referential series are determined according to The weighting of project selection criteria are obtained original data series. After that, in GRA objective by GANP. Then, according to criteria, alternative model, data are normalized in the range between zero projects are evaluated by two decision makers as using and one based on referential series. Subsequently, the grey number scale. Linguistic values are absolute data table is obtained and the grey relational transformed into grey numbers and these grey coefficient is calculated from the normalized data to numbers are transformed into whitened value by the express the relationship between the referential series whitening membership function. The data that are and original data series. At the end, the aggregated formed by whitened value are studied for the purpose grey relational grade vector is obtained by multiplying of applying GRA steps. the resulting grey relational coefficient matrix by the weights of criteria that are shown in Table 5. TUZKAYA, YOLVER 39 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company Table 6. Grey relational grades for alternatives. Alternatives Average RANK Project A 0,728 1 Project B 0,572 4 Project C 0,711 2 Project D 0,579 3 As illustrated in Table 6, the four alternative projects, [2] Mohanty, R. P., Agarwal, R., Choudhury A. K. that is Project A, Project B, Project C and Project Dare And Tiwari, M. K., 2005, “A Fuzzy ANP-Based ranked 1, 4, 2 and 3 respectively. When the results are Approach to R&D Project Selection: A Case Study” compared with the common previous opinions,high- ,International Journal of Production Research, Vol. ranked alternatives are overlapped with the most 43, No. 24, 5199–5216. expected project alternatives. However, [3] Liberatore, M. J., 1988, “An Expert Support previouslyunconsidered criteria decreased the System for R&D Project Selection” , Malhl Comput. importance level of two projects. Considering the Modelling, Vol. I I, pp. 260-265, Great Britain. results of this study,the company has chosen two projects to actualize instead of three projects. [4] Martino J. P., 1995, “Research and Development Project Selection”, Wiley Series in 5. CONCLUSION Engineering & Technology Management, New York. [5] Shakhsi-Niaei, M., Torabi, S. A. and The R&D project selection is a difficult multi-criteria Iranmanesh, S. H., 2011, “A Comprehensive decision making process to handle. The most crucial Framework for Project Selection Problem Under features of this process are complexity and especially Uncertainty and Real-World Constraints”, Computers uncertainty. As a novel approach for solution, GANP & Industrial Engineering, Vol. 61, pp. 226–237. and GRA based on grey number, have been utilized to determine the best project to actualize. These methods [6] Duan, X., Huang, M., Yang, X., Wan, B. 2013, have been used together at first time for R&D project “A Method of Partner Selection for Supply Chain selection issue. The proposed model constituted from Based on Grey-ANP in Cloud Computing”, 2013 10th two parts. The first part applies ANP based on grey Web Information System and Application Conference. number to determine the weights of the criteria. And [7] Li, G.D., Yamaguchi, D., Nagai, M. 2007, “A the second part applies GRA to rank the alternative Grey-Based Decision-Making Approach to the projects. The refrigerator projects are convenient to Supplier Selection Problem”, Mathematical and demonstrate the effectiveness of the proposed Computer Modeling 46, 573–581, Japan. methodology for selecting the best project. The method provides an objective and effective decision [8] Julong, D., 1989 “Introduction to Grey System model for selecting the most appropriate project to Theory”, The Journal of Grey System 1,1-24. develop. The analytical results of this approach show [9] Wen K. 2004, “The Grey System Analysis and that it can help to deal with complex decision making Its Application in Gas Breakdown And Var processes and provide acceptable and reasonable Compensator Finding(ø nvited Paper)”, Int. Journal of results for administrators and decision makers. computational Cognition 2(1), 21-44. Furthermore, this approach may be used for other group of projects that considered in department of [10] Saaty, T.L., 1999 “Fundamentals of the R&D system development in the home appliances Analytic Network Process”, ISAHP 1999, August 12- company. 14, Kobe, Japan. [11] Carlucci, D. and Schiuma, G., 2010, “Open Access: This article is distributed under the “Determining Key Performance Indicators – An terms of the Creative Commons Attribution License Analytical Network Approach”, Gunasekaran A. and (CC-BY 4.0) which permits any use, distribution, and Sandhu M. (Editors), Handbook on Business reproduction in any medium, provided the original Information Systems, World Scientific Publishing, author(s) and the source are credited.” ISBN 978-981-283-605-2, Chapter 21, pp. 515-536. 6. REFERENCES [12] Zhang, W., Zhang, X., Fu, X., Liu, Y., 2009, “A Grey Analytic Network Process (ANP) Model to [1] Porter, M.E., 1985, “Competitive Strategy: Identify Storm Tide Risk”, Proceedings of 2009 IEEE Techniques for Analyzing Industries and International Conference on Grey Systems and Competitors”, The Free Press. Intelligent Services, November 10-12, 2009, Nanjing, China. TUZKAYA, YOLVER 40 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company [13] Dou, Y., Zhu, Q, Sarkis, J., 2014, “Evaluating Green Supplier Development Programs with a Grey- Analytical Network Process- BasedMethodology”,European Journal of Operational Research 233, 420–431. [14] Saaty, T. L., & Vargas, L. G. 1998. “Diagnosis with Dependent Symptoms: Bayes Theorem and the Analytichierarchy Process.” Operations Research, 46(4), 491–502. [15] Sallehuddin, R., Shamsuddin, S. M. H., Hashim, S. Z. M., 2008, “Grey Relational Analysis and Its Application on Multivariate Time Series”, Proceedings of IEEE International Conference on intelligent Systems Design and Applications, vol:2. [16] Deng, J. L., (1989) “Introduction to Grey System”, Journal of Grey System, 1(1), 1-24. [17] Sreenivasulu, R., SrinivasaR., Dr.Ch (2012), “Application of Gray Relational Analysis For Surface Roughness and Roundness Error in Drilling of Al 6061 Alloy”, International Journal of Lean Thinking Vol. 3, Issue 2, December. VITAE Assoc. Prof. Dr. Umut RÕ fat TUZKAYA He is currently an associate professor in the Department of Industrial Engineering where he is teaching supply chain and logistics management, transportation management, and warehouse management courses. He received his BSc. (2000), MSc. (2002) and PhD. (2007) degrees in industrial engineering at Yildiz Technical University, Istanbul, Turkey. He has MBA degree (2003) from Istanbul Technical University, Istanbul, Turkey. He also worked as a visiting scholar in “Project of Real Time Decision Support System for Health Care” at The Logistics and Distribution Institute in University of Louisville. His research interests are logistics and supply chain management, transportation management, facility planning, and optimization techniques. Ezgi YOLVER She was born in 1992 in Istanbul, Turkey. She will graduate in June 2015 as an Industrial engineer, and receive a bachelor degree from the Yildiz Technical University, Istanbul, Turkey. She did internship in several firmand also attempted a lot of social & volunteer activitiesthrough her educational background. She is currently working as project personnel in a private company. Her interests are R&D management, project management, technology management, decision making, and she is also concerned with logistic and supply chain management. TUZKAYA, YOLVER http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Aeronautics and Space Technologies (Havacilik ve Uzay Teknolojileri Dergisi) Springer Journals

R&D Project selection by integrated grey analytic network process and grey relational analysis: an implementation for home appliances company

Download PDF
7 pages

Loading next page...
 
/lp/springer-journals/r-d-project-selection-by-integrated-grey-analytic-network-process-and-QdljlJc4ep
Publisher
Springer Journals
Copyright
Copyright © 2015 by Turkish Air Force Academy
Subject
Engineering; Aerospace Technology and Astronautics
eISSN
2148-1059
DOI
10.7603/s40690-015-0014-8
Publisher site
See Article on Publisher Site

Abstract

10.7603/s40690-015-0014-8 JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 2015 VOLUME 8 NUMBER 2 (35-41) R&D PROJECT SELECTION BY INTEGRATED GREY ANALYTIC NETWORK PROCESS AND GREY RELATIONAL ANALYSIS: AN IMPLEMENTATION FOR HOME APPLIANCES COMPANY Umut R. TUZKAYA Ezgi YOLVER YTÜ, Industrial Engineering Department, YTÜ, Industrial Engineering Department, Barbaros BulvarÕ ,34349 YÕ ldÕ z-Beú iktaú / ø stanbul Barbaros BulvarÕ , 34349 YÕ ldÕ z-Beú iktaú / ø stanbul tuzkaya@yildiz.edu.tr eyolver@gmail.com th nd Received: 28 April 2015, Accepted: 02 July 2015 ABSTRACT For many firms, the key to improve competitiveness is their ability of research and development (R&D);therefore the R&D project selection is an essential decision process for them. In this study, we worked on R&D Project Selection issue and performed an implementation for a home appliances company. Wefirst discussed important criteria for R&D projects selection with R&D specialists in the company. Inorder to evaluate projects, many criteria, containing various sub-criteria were determined via extensiveliterature research. After reviewing multi criteria decision methods in order to handle theinterdependencies among the criteria and the sub-criteria, Analytic Network Process (ANP) was chosen.Due to being conformed to characteristics of R&D projects, the ANP model generated basing on greynumbers. Also, ANP was used to get the weight of criteria. The experts filled the pairwise comparisonmatrices, which were built up for defining the importance and influences of the criteria/sub-criteria inthe ANP model. According to these matrices, weights were determined. Then, determined alternativeprojects were ranked via Grey Relational Analysis (GRA) method. The model was applied on a real liferefrigerator projects in a home appliances company. Keywords: R&D Project Selection, Grey Analytic Network Process, Grey Relational Analysis. GRø ANALø Tø K Aö SÜRECø VE GRø ø L Kø SEL ANALø Z ø LE ENTEGRE EDø LMøù AR-GE PROJELERø Nø N SEÇø Mø : EV ALETLERø ùø RKETø NDE Bø R UYGULAMA ÖZET Araú tÕ rma ve geliú tirme yetene÷ i bir çok ú irketin rekabet etme gücünü arttÕ racak önemli bir faktördür. Bu nedenle Ar-Ge projelerinin seçimi ú irketler için temel karar sürecidir. Bu çalÕ ú mada, Ar-Ge projeleri seçimi üzerine çalÕ ú Õ lmÕ ú ve bir ev aletleri ú irketinde konuyla ilgili bir uygulama yapÕ lmÕ ú tÕ r. ø lk olarakAr-Ge uzmanlarÕ yla birlikte Ar-Ge projeleri seçiminde önemli olan kriterler üzerine çalÕ ú Õ lmÕ ú tÕ r. Projeleri de÷ erlendirmek için birçok kriter ve bunlara ba÷ lÕ alt kriterler geniú bir literatür araú tÕ rmasÕ yla belirlenmiú tir. Birçok çok kriterli karar verme metodu incelendikten sonra, kriterler ve kriterler arasÕ ba÷ lÕ lÕ ÷ Õ ele almak amacÕ yla ANP metodu kullanÕ lmÕ ú tÕ r. Bu çalÕ ú mada Ar-Ge projelerinin karakteriyle uyumlu olmasÕ nedeniyle gri sayÕ lara dayalÕ ANP modeli oluú turulmuú ve kriter a÷ Õ rlÕ klarÕ nÕ n belirlenmesi için kullanÕ lmÕ ú tÕ r. ANP modelinde kriterlerin ve alt kriterlerin birbirlerine olan etkileri ve önem derecelerinin belirlenmesi için ikili karú Õ laú tÕ rma matrisleri oluú turulmuú ve uzmanlar tarafÕ ndan de÷ erlendirilmiú tir. Oluú turulan bu matrislere göre a÷ Õ rlÕ klar belirlenip, tanÕ mlanan alternatif projelerGri ø liú kisel Analiz (Gø A) metodu kullanÕ larak sÕ ralanmÕ ú tÕ r. Uygulama olarak da bir ev aletleri ú irketindeki gerçek buzdolabÕ Ar-Ge projelerinde bu modele baú vurulmuú tur. Anahtar Kelimeler: Ar-Ge Projelerinin Seçimi, Gri Analitik A÷ Süreci, Gri ø liú kisel Analiz. * TUZKAYA, YOLVER Corresponding Author øù R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company right projects in order to survive in the competitive 1. INTRODUCTION environment. The projects that will lead to success R&D project management is one of the most difficult should have a positive cost/benefit, provide the areas in projects management. In today’s world, organization to improve the chance of success, have precondition of surviving of a company in highly futuristic scope and strategic fit on stakeholder competitive environment is conducting Research and involvement [2]. Development (R&D) projects. Developed countries generally encourage the R&D activities of private The selection of R&D project is a complex decision- sector and government to improve the overall making problem encountered by most industrial firms. competitive power of the country. R&D project selection requires consideration of uncertain and/or subjective multiple criteria. The Companies that want to maintain their existence in selecting and determining relative importance of competitive environment must continually change and criteria will differ according to the goals and develop their products, services and production objectives of the sponsoring organization and the processes. This is only possible through R&D nature of the R&D activity itself [3]. activities and innovation. R&D activities generally involve scientific and technological uncertainties. A wide range of criteria and sub-criteria such as Innovations are also unpredictable, and thus involve strategic fit, capacity, technical success, funding, risks, large uncertainties. Corporate R&D management, considerations, opportunity costs, manpower, etc., are supporting the maximal use of new innovations and used for decision process [2]. Obviously, wrong technologies, always tries to keep the company up decisions in project selection have two negative with the pace of technological development. R&D consequences: (1) resources are spent on unsuitable projects are tools for the company’s management to projects and, (2) the organization loses the benefits it outpace competitors and obtain new information about could have gained if these resources had been spent on promising technologies and methods. With such new more suitable projects [4]-[5]. Therefore, most information, companies aim to defend and build companies apply the scientific selection methods that sustainable competitive advantages [1]. are generally multi criteria decision methods for R&D projects. 2. R&D PROJECT SELECTION An extensive literature review is carried out on the Around the world advanced high-tech companies are subject of R&D Project selection and investing R&D projects. R&D projects must be evaluationcriteria. R&D project selection criteria compatible with the company’s vision and mission. available in the literature are categorized into five Such projects should provide benefits for stakeholders, factors; technical, marketing, financial, environmental link with the company’s expertise and have clear and organizational factors. In this study, 12 sub- objectives in place along with built-in appropriate criteria,which are evaluated by the decision evaluation resources and have prospects of sustaining committee, are classified into these five factors. The itself. The most challenging tasks areto choose the sub-criteria that are grouped are shown in Figure 1. R&D PROJECT SELECTION CRITERIA Technical Marketing Financial Environmental Organizational Factors Factors Factors Factors Factors Existence of Probability of Probability Cost of Environmental Technical Required of Market Development Consideration Facilities Success Success Fitting Safety Advancement Degree of Investment Organizational Consideration Technology Competition Strategy Product Cost Patentability Up Figure 1. Project selection criteria. TUZKAYA, YOLVER 36 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company 3.2. Grey AnalytÕ c Network Process (GANP) 3. MULTI CRITERIA DECISION MAKING METHODS GANP method is applied for weighting of criteria using ANP and grey system theory based on In this study, multi criteria decision-making methods Saaty’sANP model. The ANP is coupling of two parts. are used on selecting of R&D projects. These methods The first consists of a control hierarchy or network can provide solutions to increasing complex ofcriteria and sub-criteria that control the interactions. management problems. Here, the background The second is a network of influences among information about the used multi criteria decision theelements and clusters. The network varies from methods is provided. Firstly, Grey System approach is criterion to criterion and a different super matrix explained. Then, Grey Analytic Network Process oflimiting influence is computed for each control (GANP) method and finally Grey Relational Analysis criterion. Finally, each of these super matrices is (GRA) method are described. weightedby the priority of its control criterion and the results are synthesized through addition for all the 3.1. Grey System Theory controlcriteria [10]. Grey theory, which was proposed by Chinese scholar Professor Deng Julong [6], is one of the new Pairwise Comparison and Local Weights mathematical theories born out of the concept of the Estimation: The ANP is based on deriving ratio grey set. It is an effective method used to solve scalemeasurements founded on pairwise comparisons uncertainty problems with discrete data and to derive ratio scale priorities for the distribution incomplete information [7]. The concept of the Grey ofinfluence among the elements and clusters of the System, in its theory and successful application, is network [11]. In the study, grey numbers were now well known in China [8]. The major advantage of applied.The parameters G1 and G1, denote the grey theory is that it can handle both incomplete smallest possible value and the largest possible value information and unclear problems very precisely. It that describea fuzzy event. Grey number scale that serves as an analysis tool especially in cases where used in this study is given in Table 1. there is insufficient data [9]. Table 1. Linguistic scales for difficulty and Õ mportance [12]. Linguistic Scale For Importance Grey Number Scale Grey Number Reciprocal Scale Just equal (E) (1, 1) (1, 1) Equally important (EI) (1/2, 3/2) (2/3, 2) Weakly more important (WMI) (1, 2) (1/2 ,1) Strongly more important (SMI) (3/2, 5/2) (2/5, 2/3) Very strongly more important (VSMI) (2, 3) (1/3, 1/2) Absolutely more important (AMI) (5/2, 7/2) (2/7, 2/5) Pairwise comparison matrices are formed by the other element with which it interacts, the super matrix decision committee by using the grey number scale. is raised to limiting Powers [14]. Before taking the limitof the matrix, it must first be reduced to a column Super Matrix Formation and Analysis: According stochastic matrix (i.e. weighted super matrix), each to the ANP approach, we need to define ofwhose column sums to unity. Then via interdependencies among factors and clusters. This is normalization, the normalized weight vectors can be also possible with super matrix formation. The found in therelevant rows of the normalized limit relative weights are aggregated into a super matrix super matrix. In this way, global weights for all based upon influence from one cluster to another, or elements will beachieved. from one factor to another within a cluster itself. The super matrix formation incorporates four elements:(1) 3.3. Grey RelatÕ onal AnalysÕ s relationships to the final objective; (2) comparisons GRA method is applied for ranking of alternative among factors and clusters; (3) comparisons projects. GRA is a new analysis method, which ofalternative relationships with respect to the factors; hasbeen proposed in the Grey system theory and it is and (4) an identity matrix for all alternatives founded by Professor Deng Julong from Huazhong (unlessthe alternatives influence each other) [13]. University of Science and Technology, People’s Republic of China [15]. Calculate The Global Weight: Finally, to yield thecumulative influence of each element on every TUZKAYA, YOLVER 37 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company GRA is used to determine the relationship between selection criteria that are used in literature with two two series of data in a grey system. Its structure R&D specialists and then we determined the hasuncertainty, therefore it handles the problems convenient ones. Secondly, the ANP model formed by consisted of discrete data and partial information [16]. the criteria and sub-criteria determined in the first It operates the grey relational grade to determine the step. Criteria have been evaluated by two decision relational degree of factors. Grey relation analysis is makers via linguistic variables that can be expressed also an effective means of analyzing the relationship in grey number. Then, a degree of grey possibility is between sequences with less data and can analyze proposed to calculate the weights. Thirdly, alternative many factors that can overcome the disadvantages of projects have been evaluated by decision makers in statistical method [17]. GRA is based on geometrical the same way with GANP method’s weighting. mathematics, which compliance with the principles of Finally the GRA model formed and alternative normality, symmetry, entirety, and proximity. GRA is projects have been ranked. A detailed implementation suitable for solving complicated interrelationships steps are given below. between multiple factors and variables. There are 3 main steps in GRA [15]. The first step is data pre- 4.1. Data GatherÕ ng And UsÕ ng The Ganp processing, the second step is locating the grey Technique relational coefficient and the final step is calculating Firstly, main factors are evaluated by using pairwise of grey relational grade. comparison matrices (assumed that there is nodependence among the factors). The decision 4. IMPLEMENTATION committee has formed pairwise comparison matrices byusing the scale given in Table 1. Linguistic scale is We have performed an implementation about R&D placed in the relevant cell against the grey project selection issue for an R&D system numberwhile evaluating. Then this scale will be development department in a home appliances transformed into whitened value by the whitening company. Various projects on refrigerator production membershipfunction and local weights are calculated processes are considered for ranking. Some of these using GANP method formulation. projects have already been actualized and some of them have not been actualized. Objective of this study Pairwise comparison matrix for the main factors is is to rank the projects according to priority and to see filled and the local weights for the main factors whether the right projects have been actualized or arecalculated as shown in Table 2. not.Firstly, we have analyzed the R&D project Table 2. Local weights and pairwise comparison matrix of main factors. MAIN FACTORS Technical Marketing Financial Environmental Organizational Local Weight Technical (1, 1) (2/5, 2/3) (1/3, 1/2) (3/2, 5/2) (2/3, 2) 0,16 Marketing (3/2, 5/2) (1, 1) (2/5, 2/3) (2, 3) (3/2, 5/2) 0,24 Financial (2, 3) (3/2, 5/2) (1, 1) (5/2, 7/2) (2, 3) 0,35 Environmental (2/5, 2/3) (2/5, 2/3) (1/3, 1/2) (1, 1) (2/5, 2/3) 0,1 Organizational (1/2, 3/2) (2/5, 2/3) (1/3, 1/2) (3/2, 5/2) (1, 1) 0,15 Sub-factors are also evaluated and weighted in the calculated in Table 3. Sub-factors of other main same way with main factors. Pairwise factors are also evaluated and weighted in the same comparisonmatrix for sub-factors of technical factors way. is filled and the local weights for their sub-factors are Table 3. Local weights and pairwise comparison matrix of sub-factors of technical factor. Probability of Advancement TECHNICAL FACTORS Patentability Local Weights technical success technology Probability of technical success (1, 1) (2, 3) (3/2, 5/2) 0,511 Advancement technology (1/3, 1/2) (1, 1) (2/5, 2/3) 0,182 Patentability (2/5, 2/3) (3/2, 5/2) (1, 1) 0,307 Afterwards, interdependent weights of the main each factor on every other factor using pairwise factors are calculated and the dependencies among comparisons. Same linguistic variable scale is used themain factors are considered. Dependence among again. Allthe grey evaluation matrices are produced in the factors is determined by analyzing the impact of the same manner. Then this scale will be transformed TUZKAYA, YOLVER 38 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company intowhitened value by the whitening membership After pairwise comparisons for technical factors are function and local weights are calculated using GANP completed, the resulting relative importance weight method formulation. sare presented in Table 4. Table 4. The inner dependence matrix of the factors with respect to ‘‘Technical Factors”. Relative TECHNICAL Marketing Financial Environmental Organizational Importance FACTORS Weight Marketing (1, 1) (2/3, 2) (1, 2) (3/2, 5/2) 0,32 Financial (1/2, 3/2) (1, 1) (1, 2) (3/2, 5/2) 0,3 Environmental (1/2, 1) (1/2, 1) (1, 1) (1, 2) 0,22 Organizational (2/5, 2/3) (2/5, 2/3) (1/2, 1) (1, 1) 0,16 Same operations are generated for the sub-factors of dependence matrices are multiplied with the local each main factor and inner dependence relative weights of the factors. The result of the GANP, Table importance weights are obtained. Finally, to compute 5 is obtained. the interdependent weights of the factors, these inner Table 5. Computed weights. Main Criteria (Factors) Factors Local Weights Sub-Criteria (Sub-Factors) Local Weights Probability of technical success 0,511 Technical Factors 0,19 Advancement technology 0,182 Patentability 0,307 Probability of market success 0,414 Marketing Factors 0,2 Degree of competition 0,586 Cost of development 0,203 Financial factors 0,28 Investment 0,353 Product Cost Up 0,444 Environmental considerations 0,253 Environmental Factors 0,17 Safety considerations 0,747 Existence of required facilities 0,29 Organizational Factors 0,16 Fitting organizational strategy 0,71 4.2. Application of The Gra Technique Then referential series are determined according to The weighting of project selection criteria are obtained original data series. After that, in GRA objective by GANP. Then, according to criteria, alternative model, data are normalized in the range between zero projects are evaluated by two decision makers as using and one based on referential series. Subsequently, the grey number scale. Linguistic values are absolute data table is obtained and the grey relational transformed into grey numbers and these grey coefficient is calculated from the normalized data to numbers are transformed into whitened value by the express the relationship between the referential series whitening membership function. The data that are and original data series. At the end, the aggregated formed by whitened value are studied for the purpose grey relational grade vector is obtained by multiplying of applying GRA steps. the resulting grey relational coefficient matrix by the weights of criteria that are shown in Table 5. TUZKAYA, YOLVER 39 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company Table 6. Grey relational grades for alternatives. Alternatives Average RANK Project A 0,728 1 Project B 0,572 4 Project C 0,711 2 Project D 0,579 3 As illustrated in Table 6, the four alternative projects, [2] Mohanty, R. P., Agarwal, R., Choudhury A. K. that is Project A, Project B, Project C and Project Dare And Tiwari, M. K., 2005, “A Fuzzy ANP-Based ranked 1, 4, 2 and 3 respectively. When the results are Approach to R&D Project Selection: A Case Study” compared with the common previous opinions,high- ,International Journal of Production Research, Vol. ranked alternatives are overlapped with the most 43, No. 24, 5199–5216. expected project alternatives. However, [3] Liberatore, M. J., 1988, “An Expert Support previouslyunconsidered criteria decreased the System for R&D Project Selection” , Malhl Comput. importance level of two projects. Considering the Modelling, Vol. I I, pp. 260-265, Great Britain. results of this study,the company has chosen two projects to actualize instead of three projects. [4] Martino J. P., 1995, “Research and Development Project Selection”, Wiley Series in 5. CONCLUSION Engineering & Technology Management, New York. [5] Shakhsi-Niaei, M., Torabi, S. A. and The R&D project selection is a difficult multi-criteria Iranmanesh, S. H., 2011, “A Comprehensive decision making process to handle. The most crucial Framework for Project Selection Problem Under features of this process are complexity and especially Uncertainty and Real-World Constraints”, Computers uncertainty. As a novel approach for solution, GANP & Industrial Engineering, Vol. 61, pp. 226–237. and GRA based on grey number, have been utilized to determine the best project to actualize. These methods [6] Duan, X., Huang, M., Yang, X., Wan, B. 2013, have been used together at first time for R&D project “A Method of Partner Selection for Supply Chain selection issue. The proposed model constituted from Based on Grey-ANP in Cloud Computing”, 2013 10th two parts. The first part applies ANP based on grey Web Information System and Application Conference. number to determine the weights of the criteria. And [7] Li, G.D., Yamaguchi, D., Nagai, M. 2007, “A the second part applies GRA to rank the alternative Grey-Based Decision-Making Approach to the projects. The refrigerator projects are convenient to Supplier Selection Problem”, Mathematical and demonstrate the effectiveness of the proposed Computer Modeling 46, 573–581, Japan. methodology for selecting the best project. The method provides an objective and effective decision [8] Julong, D., 1989 “Introduction to Grey System model for selecting the most appropriate project to Theory”, The Journal of Grey System 1,1-24. develop. The analytical results of this approach show [9] Wen K. 2004, “The Grey System Analysis and that it can help to deal with complex decision making Its Application in Gas Breakdown And Var processes and provide acceptable and reasonable Compensator Finding(ø nvited Paper)”, Int. Journal of results for administrators and decision makers. computational Cognition 2(1), 21-44. Furthermore, this approach may be used for other group of projects that considered in department of [10] Saaty, T.L., 1999 “Fundamentals of the R&D system development in the home appliances Analytic Network Process”, ISAHP 1999, August 12- company. 14, Kobe, Japan. [11] Carlucci, D. and Schiuma, G., 2010, “Open Access: This article is distributed under the “Determining Key Performance Indicators – An terms of the Creative Commons Attribution License Analytical Network Approach”, Gunasekaran A. and (CC-BY 4.0) which permits any use, distribution, and Sandhu M. (Editors), Handbook on Business reproduction in any medium, provided the original Information Systems, World Scientific Publishing, author(s) and the source are credited.” ISBN 978-981-283-605-2, Chapter 21, pp. 515-536. 6. REFERENCES [12] Zhang, W., Zhang, X., Fu, X., Liu, Y., 2009, “A Grey Analytic Network Process (ANP) Model to [1] Porter, M.E., 1985, “Competitive Strategy: Identify Storm Tide Risk”, Proceedings of 2009 IEEE Techniques for Analyzing Industries and International Conference on Grey Systems and Competitors”, The Free Press. Intelligent Services, November 10-12, 2009, Nanjing, China. TUZKAYA, YOLVER 40 R&D Project Selection By Integrated Grey Analytic Network Process And Grey Relational Analysis: An Implementation For Home Appliances Company [13] Dou, Y., Zhu, Q, Sarkis, J., 2014, “Evaluating Green Supplier Development Programs with a Grey- Analytical Network Process- BasedMethodology”,European Journal of Operational Research 233, 420–431. [14] Saaty, T. L., & Vargas, L. G. 1998. “Diagnosis with Dependent Symptoms: Bayes Theorem and the Analytichierarchy Process.” Operations Research, 46(4), 491–502. [15] Sallehuddin, R., Shamsuddin, S. M. H., Hashim, S. Z. M., 2008, “Grey Relational Analysis and Its Application on Multivariate Time Series”, Proceedings of IEEE International Conference on intelligent Systems Design and Applications, vol:2. [16] Deng, J. L., (1989) “Introduction to Grey System”, Journal of Grey System, 1(1), 1-24. [17] Sreenivasulu, R., SrinivasaR., Dr.Ch (2012), “Application of Gray Relational Analysis For Surface Roughness and Roundness Error in Drilling of Al 6061 Alloy”, International Journal of Lean Thinking Vol. 3, Issue 2, December. VITAE Assoc. Prof. Dr. Umut RÕ fat TUZKAYA He is currently an associate professor in the Department of Industrial Engineering where he is teaching supply chain and logistics management, transportation management, and warehouse management courses. He received his BSc. (2000), MSc. (2002) and PhD. (2007) degrees in industrial engineering at Yildiz Technical University, Istanbul, Turkey. He has MBA degree (2003) from Istanbul Technical University, Istanbul, Turkey. He also worked as a visiting scholar in “Project of Real Time Decision Support System for Health Care” at The Logistics and Distribution Institute in University of Louisville. His research interests are logistics and supply chain management, transportation management, facility planning, and optimization techniques. Ezgi YOLVER She was born in 1992 in Istanbul, Turkey. She will graduate in June 2015 as an Industrial engineer, and receive a bachelor degree from the Yildiz Technical University, Istanbul, Turkey. She did internship in several firmand also attempted a lot of social & volunteer activitiesthrough her educational background. She is currently working as project personnel in a private company. Her interests are R&D management, project management, technology management, decision making, and she is also concerned with logistic and supply chain management. TUZKAYA, YOLVER

Journal

Journal of Aeronautics and Space Technologies (Havacilik ve Uzay Teknolojileri Dergisi) – Springer Journals

Published: Sep 23, 2015

References

  • A Fuzzy ANP-Based Approach to R & D Project Selection: A Case Study
    Mohanty, R. P.; Agarwal, R.; Choudhury, A. K.; Tiwari, M. K.
  • “An Expert Support System for R & D Project Selection”
    Liberatore, M. J.
  • A Comprehensive Framework for Project Selection Problem Under Uncertainty and Real-World Constraints
    Shakhsi-Niaei, M.; Torabi, S. A.; Iranmanesh, S. H.
  • A Grey-Based Decision-Making Approach to the Supplier Selection Problem
    Li, G.D.; Yamaguchi, D.; Nagai, M.
  • Introduction to Grey System Theory
    Julong, D.
  • “The Grey System Analysis and Its Application in Gas Breakdown And Var Compensator Finding(İnvited Paper)”
    Wen, K.
  • Evaluating Green Supplier Development Programs with a Grey-Analytical Network Process-BasedMethodology
    Dou, Y.; Zhu, Q; Sarkis, J.
  • Diagnosis with Dependent Symptoms: Bayes Theorem and the Analytichierarchy Process
    Saaty, T. L.; Vargas, L. G.
  • Introduction to Grey System
    Deng, J. L.