A combined methodology for supplier selection and performance evaluation A combined methodology for supplier selection and performance evaluation Mithat Zeydan a,⇑, Cüneyt Çolpan b, Cemal Çobanoğlu c a Department of Industrial Engineering, Engineering Faculty, Erciyes University, 38039 Kayseri, Turkey b Department of Quality Assurance, 2nd Turkish Air Supply and Maintenance Center Command, Kayseri, Turkey c Department of Procurement, Hyundai Assan Automotive Factory, _Izmit/Kocaeli, Turkey a r t i c l e i n f o Keywords: Supplier evaluation Multi-criteria decision making techniques Performance improvement a b s t r a c t Today, organizations that wish to carry on the sustainable growing need a robust strategic performance measurement and evaluation system because of changing demands of consumers, reduced product life cycle, competitive and globalised markets. In this study, a new methodology is introduced and proposed for increasing the supplier selection and evaluation quality. The new approach considers both qualitative and quantitative variables in evaluating performance for selection of suppliers based on efficiency and effectiveness in one of the biggest car manufacturing factory in Turkey. This new methodology is realized in two steps. In the first stage, qualitative performance evaluation is performed by using fuzzy AHP (Ana- lytical Hierarchical Process) in finding criteria weights and then fuzzy TOPSIS (Technique for Order Pref- erence by Similarity to Ideal Solution) is utilized in finding the ranking of suppliers. So, qualitative variables are transformed into a quantitative variable for using in DEA (Data Envelopment Analysis) methodology as an output called quality management system audit. In the second stage, DEA is per- formed with one dummy input and four output variables, namely, quality management system audit, warranty cost ratio, defect ratio, quality management. As a result, comparing with the present system applied by the car factory, the new method seems to be some advantages and superiorities for making the decision in buying the quality car luggage side part (panel) by selecting the suitable supplier(s) in an automotive factory of Turkey. � 2010 Elsevier Ltd. All rights reserved. 1. Introduction To choose the right supplier deals, with an important evalua- tion, and selection problems in the purchasing function of a busi- ness. A good supplier selection makes a significant difference to an organization’s future to reduce operational costs and improve the quality of its end products. There have been a lot of factors in today’s global market in which that influence companies to search for a competitive advantage by focusing on purchasing raw mate- rials and component parts represents the largest percentage of the total product cost. For instance, high technology products such as motor vehicles, railroad&transport equipment, machinery&equip- ment components, purchased materials and services account for up to 80% of the total product cost. Therefore, selecting the right suppliers is a key to the procurement process and represents a ma- jor opportunity for companies to reduce costs. On the other hand, selecting the wrong suppliers can cause operational and financial problems (Weber, Current, & Benton, 1991). The traditional ap- proach to supplier selection has been to select suppliers solely on the basis of price for many years. However, as companies have learned that price as a single criterion for supplier selection is insufficient, they have turned into more comprehensive multi-cri- teria decision making techniques. Recently, these criteria have be- come increasingly complex as environmental, social, political, and customer satisfaction concerns have been added to the traditional factors of quality, delivery, cost, and service. Apart from cost reduc- tion, companies continuously work with suppliers to remain com- petitive by reducing product development time, improving product quality, and reducing lead times. For instance, a qualified base of suppliers helps a company achieve greater innovation through im- proved product design and increased flexibility. Some authors have identified several criteria for supplier selection, such as the net price, quality, delivery, historical supplier performance, capacity, communication systems, service, and geographic location, among others (Dempsey, 1978). These evaluation criteria involve trade- offs and are a key issue in the supplier assessment process since it measures the performance of suppliers. For example, one vendor may offer inexpensive parts of slightly below average quality, while another vendor may offer higher quality parts, with uncer- tain delivery thus setting up trade-offs. In addition, the importance of each criterion, varies from one purchase to the next and is com- plicated further by the fact that some criteria are quantitative (price, quality, etc.), while others are qualitative (service, flexibil- ity, etc.). Thus, a technique is needed that can adjust for the deci- sion maker’s attitude toward the importance of each criterion 0957-4174/$ - see front matter � 2010 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2010.08.064 ⇑ Corresponding author. Tel.: +90 352 4374901/32454; fax: +90 352 4375784. E-mail address: mzeydan@erciyes.edu.tr (M. Zeydan). Expert Systems with Applications 38 (2011) 2741–2751 Contents lists available at ScienceDirect Expert Systems with Applications j o u r n a l h o m e p a g e : w w w . e l s e v i e r . c o m / l o c a t e / e s w a http://dx.doi.org/10.1016/j.eswa.2010.08.064 mailto:mzeydan@erciyes.edu.tr http://dx.doi.org/10.1016/j.eswa.2010.08.064 http://www.sciencedirect.com/science/journal/09574174 http://www.elsevier.com/locate/eswa and incorporates both qualitative and quantitative factors (Bhutta & Huq, 2002). The overall objective of the supplier evaluation pro- cess is to reduce risk and maximize overall value to the purchaser. An effective supplier survey should have certain characteristics such as comprehensiveness, objectiveness, reliability, flexibility and finally, it has to be mathematically straightforward. It can be concluded that important savings can be realized through effective purchasing strategies. This study helps decision makers reduce a base of potential suppliers to a manageable number and make the supplier selection by means of multi-criteria techniques. This new methodology was applied to a car manufacturing facility in Turkey. 2. Literature review Supplier evaluation is a multi-objective and criteria decision making problem containing many quantitative and qualitative fac- tors because there are typically more than one criterion (attitude) needed to be taken into consideration in evaluating a supply source. All of supply sources are focused on their performance such as delivery, quality, service and price as the main factors that all firms use for evaluating sources of supply (Ha & Krishnan, 2008). Many firms and researchers have been working on the supplier evaluation problem over the past decade to develop decision mak- ing models which can effectively deal with this problem. According to Ghodsypour and O’Brien (1998), optimization models for sup- plier evaluation can be classified into two groups: single objective models which are used to consider one criterion as the objective function and other criteria as constraints. The single objective models have two disadvantages: all criteria are equally weighted, which rarely happens in practice, and they have significant difficul- ties in considering qualitative factors. In contrast, the multiple objective models have been applied to a supplier evaluation prob- lem. Relying on a single criterion makes the supplier selection pro- cess risky. Therefore, a multi-criteria approach is recommended. A pioneering work in supplier selection criteria was that of Dickson in 1966. Despite the multiple criteria nature of the problem, very little work has been devoted to the study of the supplier selection problem by using multi-criteria techniques such as goal program- ming, multi-objective programming, or other similar approaches. Kahraman, Cebeci, and Ulukan (2003) used fuzzy AHP to select the best supplier for a manufacturer firm established in Turkey. Bevilacqua and Petroni (2002) developed a system for supplier selection using fuzzy logic. Some authors as used in this paper have combined decision models in the supplier selection process, for example, Weber, Current, and Desai (1998) combined DEA and mathematical programming models. This combination provided decision makers with a tool for negotiating with suppliers. Dickson (1966) developed a model combining mathematical programming model and TCO (total cost of ownership). They derived the inven- tory management policy using activity-based costing information. Ghodsypour and O’Brien (1998) used AHP and mathematical pro- gramming to determine the best order quantity allocation while considering qualitative criteria into the analysis. Xia and Wu (2007) presented an integrated approach of AHP improved by rough sets theory and multi-objective mixed integer programming. Dulmin and Mininno (2003) applied a model to a mid-sized Italian firm operating in the field of public road and rail transportation by applying a multi-criteria decision making technique (promethee/ gaia) to supplier selection problem. The supplier selection problem is complicated and risky, owing to a variety of qualitative and quantitative factors affecting the decision making process. There have been several supplier selection methods available in the liter- ature. Some authors propose linear weighting models in which suppliers are rated on several criteria and in which these ratings are combined into a single score. These models include the cate- gorical method which relies heavily on the experience and ability of the individual buyer, the weighted point (Timmerman, 1986) and the analytical hierarchical process (Nydick & Hill, 1992). Total cost approaches attempt to quantify all costs related to the selec- tion of a vendor in monetary units, this approach includes cost ra- tio (Timmerman, 1986) and total cost of ownership (Dulmin & Mininno, 2003). Mathematical programming models often con- sider only the more quantitative criteria; this approach includes the principal component analysis (Petroni & Braglia, 2000) and neural network (Lovell & Pastor, 1999). The neural network for supplier selection is another method that has been developed to help selecting the best supplier. Com- paring to conventional models for decision support system, neural networks save a lot of time and money of system development. The supplier-selecting system includes two functions: one is the func- tion measuring and evaluating performance of purchasing (quality, quantity, timing, price and costs) and storing the evaluation in a database to provide data sources to neural network. The other is the function using neural network to select suppliers. ANN was also applied to the supplier evaluation problem by imitating the decision process of a buyer for supplier selection (Lovell & Pastor, 1999). Nevertheless, these models are still lacking of the capability to deal with uncertainty which is usually present in the supplier selection problem. Carrera and Mayorga (2008) proposed a Fuzzy Inference System (FIS) approach in supplier selection for new prod- uct development. Experts agree that no best way exists to evaluate and select suppliers (Bello, 2003), and thus organizations use a variety of approaches and implements the one that suits best depending on the company’s particular requirements. Many previ- ous researches, in vendor evaluation, emphasizes conceptual and empirical decision support models that may suffer from certain shortcomings, such as being mathematically too complex or too subjective. Practical appreciation needs a methodology that is sim- ple to use and understand, but yet it shall produce reasonably accurate results. There have been a lot of hybrid methods em- ployed in the last 10 years at the literature in terms of supplier evaluation and selection methods (Morlacchi, 1999; Simpson, Si- guaw, & White, 2003; Weber, Current, & Desai, 2000; Wang, Huang, & Dismukes, 2004; Bello, 2003). Fuzzy AHP, fuzzy TOPSIS and DEA are commonly used in the literature separately or some- times their combinations can be used at the same time. There has not been any study in the literature about a hybrid fuzzy AHP/fuz- zy TOPSIS/DEA approach before. When the literature is widely looked through, MCDM (Multi-Criteria Decision Making) tech- niques generally used are focused on TOPSIS (or fuzzy TOPSIS), AHP (or fuzzy AHP) and DEA. There have been some advantages and disadvantages when compared with each other, in terms of AHP and TOPSIS (Zeydan & Çolpan, 2009). Also, fuzzy AHP and fuz- zy TOPSIS are combined in this study. But, it is the first time in the literature that weights are used by transforming qualitative vari- ables into only one quantitative variable in fuzzy TOPSIS and found as triangular fuzzy numbers with fuzzy AHP. The hybrid method in the first step uses fuzzy AHP to assign criteria weight and then ranks all suppliers for the qualitative selection by using fuzzy TOP- SIS. The result obtained from fuzzy TOPSIS is used in DEA as an out- put variable called quality management system audit (QMSA). In the second step, it uses DEA methodology in order to choose effi- cient vendors in the final selection process. 3. Proposed hybrid method for supplier selection and evaluation We used three multi-criteria decision making method to find efficient and inefficient suppliers sensitively. In the first step, these are fuzzy AHP for the determination of criteria weights and fuzzy 2742 M. Zeydan et al. / Expert Systems with Applications 38 (2011) 2741–2751 https://isiarticles.com/article/19255