A rough set based approach to distributor selection in supply chain management

https://doi.org/10.1016/j.eswa.2010.06.021Get rights and content

Abstract

Distributor’s selection is an important issue in Supply chain management, particularly in the current competitive environment. The current research works provide only conceptual, descriptive, and simulation results, focusing mainly on firm resources and general marketing factors. The selection and evaluation of distributors generally incorporate qualitative information; however, analyzing qualitative information is difficult by standard statistical techniques. Consequently, a more suitable approach is desired. In this paper, a method based on Rough set theory, which has been recognized as a powerful tool in dealing with qualitative data in the literature, is introduced and modified for preferred distributor selection. We derived certain decision rules which are able to facilitate distributor selection and identified several significant features based on an empirical study conducted in China.

Introduction

Industry is now strongly recognizing that total management of the supply chain enhances the competitive edge of all “players” therein. As a result, Supply chain management (SCM) has received more attentions from both academicians and practitioners in the past decade. Many articles and books have been published for the methods and opinions about the application of supply chain management. Although there is no generally accepted notion of supply chain, at least it should contain the suppliers’ suppliers and the customers’ customers. Supply chain in this paper refers to a network of integrated and dependent process through which specifications are transformed to finished deliverables. Fig. 1 depicts a conceptual framework for supply chain.

Supplier selection and evaluation play an important role in the supply chain process and are crucial to the success of manufacturing firms (Sevkli, Lenny Koh, Zaim, Demirbag, & Tatoglu, 2008). There are many researchers in supplier selection, and many methodologies are applied in practice, such as the cost-ratio method, linear or mixed integer programming to goal and multi-objective linear programming models (Ghodsypour and O’Brien, 1998, Oliveria and Lourenco, 2002, Yan et al., 2003). Although these methods have been widely used in the area of supplier selection, there are certain drawbacks associated with the implementation of these methods. Apart from these traditional methods for supplier selection, recently fuzzy systems theory has been successfully applied to supplier selection problems (Chan and Kumar, 2007, Kahraman et al., 2004, Kahraman et al., 2003), and Rough set theory (RST) has also been applied for preferred suppliers prediction (Tseng, Huang, Jiang, & Ho, 2006).

To date, numerous literatures have explored the issues of supplier selection. In contrast, little work has been done in selection of distributor, particularly in empirical studies. Only conceptual, descriptive and simulation results focused primarily on firm resources and general marketing/selling factors were discussed (Abratt and Pitt, 1989, Cavusgil et al., 1995, Shipley et al., 1989, Yeoh and Calantone, 1995). It should be noted that distributor selection has not been studied deeply and the theoretical methods developed by academics have not been fully applied in industry. In this paper, we propose a rough set based methodology which is able to perform rule induction effectively. Moreover, the weight of each input feature is incorporated in the proposed approach so as to enhance quality of the derived rules.

The remainder of this paper is organized as follows: The next section introduces the background of distributor rough set theory and the standard rough set-based rule induction problem. Section 3 presents the basic rule identification algorithm to determine the reducts with both equal and unequal weight features. A case study is presented to show how the rule identification approach can be applied to distributor selection in Section 4. Section 5 concludes the paper with discussion of empirical findings and future research directions.

Section snippets

Literature review on distributor research

As mentioned above, there are few empirical studies for manufacturers’ distributor selection. Ross (1973) studied the selection of the overseas distributor. The author concluded that whether or not the exporter will be able to achieve his goals depends to a great extent on how well he has carried out his analysis of which firm will do the best possible job for him in a particular market. Lindqvist (1983) reviewed the research trends in distribution in Finland and found that the factors

Rule identification algorithms

The proposed conceptual framework to elicit decision rules consists of the following steps: problem definition, data preparation, data partition, reduct generation, and rule-validation as shown in Fig. 2.

Case studies

The distributor selection is an important issue in supply chain management, especially in the current competitive marketing environment. Although the distributors face increasing challenges in a competitive environment (Kalafatis, 2000, Mudambi and Aggarwal, 2003), the power of distributors’ in marketing channels is getting stronger and stronger, which give much advantages in negotiation with vendors and buyers and makes it more crucial in selecting a good distributor for manufacturers.

Conclusions

In this paper, distributors’ selection is analyzed based on the rough set theory approach in both equal and unequal weight features. Through this method, several rules are generated for distributors’ evaluation and selection. The result not only shows the effectiveness of unequal weight incorporated rules identification, but also it shows the importance of the relationship intensity, marketing experience, and the management ability in selecting the distributors. These rules have been proved to

References (38)

  • M. Beynon et al.

    Knowledge discovery in marketing: An approach through rough set theory

    European Journal of Marketing

    (2001)
  • C.-F. Chien et al.

    Using rough set theory to recruit and retain high-potential talents for semiconductor manufacturing

    IEEE Transactions on Semiconductor Manufacturing

    (2007)
  • M. Daubie et al.

    A comparison of the rough sets and recursive partitioning induction approaches: An application to commercial loans

    International Transactions in Operational Research

    (2002)
  • D. Dubois et al.

    Rough fuzzy sets and fuzzy rough sets

    International Journal of General Systems

    (1990)
  • P. Fonsson et al.

    Achieving high satisfaction in supplier–dealer working relationships

    Supply Chain Management: An International Journal

    (2003)
  • E.H. Fram

    We can do a better job of selecting international distributors

    Journal of Business and Industrial Marketing

    (1992)
  • S. Greco et al.

    Extension of the rough set theory approach to multicriteria decision support

    INFOR

    (2000)
  • Heckerman, D., Mannila, H., Pregibon, D., & Uthurusamy, R. (1997). In Proceedings of 3rd international conference on...
  • C. Kahraman et al.

    Multi-criteria supplier selection using fuzzy AHP

    Logistics Information Management

    (2003)
  • Cited by (48)

    • Going downstream in a project-based firm: Integration of distributors in the delivery of complex systems

      2019, International Journal of Project Management
      Citation Excerpt :

      Moreover, willingness to maintain sufficient inventory, willingness to commit advertising dollars, commitment to achieving minimum sales targets, undivided attention to product, willingness to invest in sales training, and willingness to drop competing product lines (Cavusgil et al., 1995) can be considered relationship capabilities. Previous studies mainly studied capability attributes through surveys in industrial manufacturing firms (Kaleka, 2002; Lin and Chen, 2008; Zou et al., 2011) or analyzed manufacturers' perspectives through interviews (Cavusgil et al., 1995; Sharma et al., 2007). In such studies, the focal firms have been industrial manufacturing firms that produce standard equipment in medium to high volumes instead of customer-specifically tailored complex systems and solutions.

    • CLUS-MCDA: A novel framework based on cluster analysis and multiple criteria decision theory in a supplier selection problem

      2018, Computers and Industrial Engineering
      Citation Excerpt :

      Zhao and Yu (2011) proposed a case-based reasoning considering data mining and clustering for attribute weight calculation in entropy with back-propagation neural networks for the petroleum industry in China. Zou, Tseng(Bill), Sohn, Song, and Gutierrez (2011) proposed an empirical study based on rough set theory to derive decision rules to select the optimal distributor. Masciari (2012) suggested a system based an outlier template definition for monitoring anomalies in RFID data streams in supply chains.

    • Rough set based rule induction in decision making using credible classification and preference from medical application perspective

      2016, Computer Methods and Programs in Biomedicine
      Citation Excerpt :

      Approximation constitutes two basic operations in the rough set approach [32,46]. Recently, RST has been investigated in certain areas such as fault diagnosis [47–50], interval data clustering [51–54], supply chain management [55–58], image analysis [50,59,60], knowledge acquisition [61–63], manufacturing quality control [64,65], customer relationship management [66–68]. However, these conventional rough set approaches cannot guarantee that the categorization of a decision table is credible.

    • Rule induction for hierarchical attributes using a rough set for the selection of a green fleet

      2015, Applied Soft Computing Journal
      Citation Excerpt :

      The adjective, “vague”, refers to the quality of information and defines the inconsistency or ambiguity that follows from information granulation [47,48]. RST has become the subject of much study and many applications in many areas, such as parallel computing [26], supply chain management [11,22,33,46], wave height prediction [1], text categorization [32], the prediction of debris flow disasters [30], rural development [3], webpage classification and Web services composition [9,25], electronic noses [2], IC packaging foundry [17], linguistic terms [16], elementary education [43], environmental performance evaluation [29], medical science [6,8,23,41], economic and financial prediction [9,42], the airline market [24], customer relationship management [37,39], transportation [4,20] and other real-life applications [12,18,19]. RST is successful because: (i) only the facts that are hidden in data are analyzed, (ii) no additional information about the data is required, such as thresholds or expert knowledge, and (iii) a minimal knowledge representation can be attained [31].

    View all citing articles on Scopus
    View full text