Research paper Development of a case based intelligent supplier relationship management system linking supplier rating system and

d product coding system

King L. Choy, Wing Bun Lee and Victor Lo
The authors King L. Choy is an Assistant Professor and Wing Bun Lee is Chair Professor at Hong Kong Polytechnic University, Hong Kong, PRC. Victor Lo is Vice-President Asia Operations, Honeywell Consumer Products (Hong Kong) Limited, Hong Kong, PRC. Keywords Customer relations, Supplier relations, Supply chain management, Help desks, Product information Abstract An intelligent supplier relationship management system (ISRMS) integrating a company's customer relationship management (CRM) system, supplier rating system (SRS) and product coding system (PCS) by the case based reasoning (CBR) technique to select preferred suppliers during the new product development (NPD) process is discussed. By using ISRMS in Honeywell Consumer Product (Hong Kong) Limited, it is found that the outsource cycle time from the searching of potential suppliers to the allocation of order, as well as the delay in delivery of goods of suppliers after order allocation, are greatly reduced. In addition, performance of suppliers can be monitored effectively. Electronic access The Emerald Research Register for this journal is available at www.emeraldinsight.com/researchregister The current issue and full text archive of this journal is available at www.emeraldinsight.com/1359-8546.htm
Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . pp. 86-101 # Emerald Group Publishing Limited . ISSN 1359-8546 DOI 10.1108/13598540410517601

1 Introduction
Customer relationship management (CRM) has become very important in the competitive business environment since the late 1990s and is now a multimillion-dollar industry. In increasingly competitive markets, customer satisfaction is a vital corporate objective. Key elements to increasing customer satisfaction include producing consistently high-quality products and providing high-quality customer service. In addition, the intensive global competition among manufacturers to co-ordinate and respond quickly to the industry value chain from suppliers to customers has made customer-supplier relationship management important in the new business era. In such circumstances the decision making in each business plays a key role in the cost reduction, and supplier selection is one of the important functions in the supplier relationship management because doing business with appropriate suppliers is beneficial for the organization to provide a sufficient production volume with good quality. Very few manufacturers now own all the activities along the chain but integrate the supply network from various supplier networks and the ability to make fast and accurate decisions often constitute a competitive advantage compared with competitors or other networks. The rapid advance in information technology is now deployed not only to improve the existing operational effectiveness of a business, but also to build the new capability to meet today's business environment and complexity. Consequently, top management may find it difficult to select the most appropriate supplier. Supplier relationship management (SRM), a new category of supply chain applications, contributes to the supplier selection and thus increases the competitive advantage of the manufacturer through three primary mechanisms: (1) support of improved business processes across the supply chain; (2) a next-generation architecture that can handle multi-enterprise processes; and
The authors wish to thank the Research Committee of the Hong Kong Polytechnic University for its support to the project.

86

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

(3) facilitation of rapid product cycles and new product introduction. Together, these mechanisms can drive competitive advantage through substantial reductions in the true cost of parts and materials, increased flexibility to respond to changes in customer demand, and faster cycle times which can enhance customer satisfaction and increase market share. The design of a supplier relationship management (SRM) to facilitate supplier selection using an integrative case based supplier selection and help desk approach to select appropriate suppliers together with their past performance has become a promising solution for manufacturers to identify preferred suppliers and trading partners to form a supply network on which they depend for products, components, services and distribution. The result is the formation of an integrated supply network that allows the most appropriate suppliers of the manufacturers to deliver the competitively priced, high quality products and services to their final customers according to their demand. By using ISRMS, manufacturers can shortlist appropriate suppliers according to the position the supplier is ranked, which in turn is made according to the suitability of the supplier attributes selected. In summary, the outsourcing cycle time from the searching of potential suppliers to the allocation of orders to the most appropriate supplier can be greatly reduced with high accuracy. In addition, performance of suppliers can be monitored effectively. This paper is divided into seven sections. Section 2 introduces CRM and SRM. Section 3 discusses the suitability of adopting CBR technique in supplier selection, which is a function of SRM. Section 4 is the development of ISRMS using a CBR system incorporating major tasks in SRM to form a distinct intelligent supplier evaluation system with the aid of the help desk module to retrieve past performance records, which is important for manufacturers wishing to outsource operations to reliable, suitable suppliers and business partners. The procedures for constructing the cased based supplier selection module (CSSM) integrating the company's supplier rating system (SRS) and product coding system 87

(PCS), which are critical for the success of ISRMS, are also detailed in this section. Section 5 is about the application case study, results and benefits by using ISRMS as an intelligent supplier relationship management system in the purchasing department of Honeywell Consumer Product (Hong Kong) Limited, to aid the conventional human reasoning process of supplier selection during the new product development (NPD) process as well as monitoring supplier performance periodically to ensure that a satisfactory level of performance can be achieved. The results and benefits of using ISRMS are discussed in Section 6. Finally, a conclusion of the application of ISRMS is made in Section 7.

2 Customer and supplier relationship management (CRM/SRM)

CRM is a process by which a company maximizes customer information in an effort to increase loyalty and retain customers' business over their lifetimes. The primary goals of CRM are to first, build long term and profitable relationships with chosen customers, second, get closer to those customers at every point of contact, and third, maximize the company's share of the customer's wallet (Shaw, 1999). In fact CRM is an information industry term for methodologies, software, and usually Internet capabilities that help an enterprise manage customer relationships in an organized way. Simply stated, CRM is about finding, getting, and retaining customers. In the Internet age, CRM accesses the new markets everywhere throughout the World Wide Web (www) to access the world class capabilities and consequently increase the commoditization by shortening the product life cycle, and eroding margins. CRM enriches the competitiveness by increasing customer choices while purchasing product, making use of technology to perform the information empowerment, developing new markets and new business models and also increasing the connectivity between all relative parties within a business. As the trend toward use of technology to drive competitive advantage has taken root, visionary manufacturers are starting to take advantage of a new competitive opportunity called supplier

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

relationship management (SRM). Herrmann and Hodgson (2001) defined SRM as a process involved in managing preferred suppliers and finding new ones whilst reducing costs, making procurement predictable and repeatable, pooling buyer experience and extracting the benefits of supplier partnerships. It is focused on maximizing the value of a manufacturer's supply base by providing an integrated and holistic set of management tools focused on the interaction of the manufacturer with its suppliers. In fact, there exists an interesting and satisfying symmetry between the role of CRM and SRM in the manufacturing environment, as illustrated in Figure 1. By integrating CRM with SRM properly through the process of product design and development, and the application of supply chain management under the same platform of an ERP system, SRM solutions can provide significant competitive advantage by delivering value in three important areas. They are: (1) the dramatic cost savings; (2) the increasing flexibility and responsiveness to customer requirements; and (3) substantially faster cycle times. Together these benefits can lead to meaningful faster time to market share in the course of the product life cycle based on the customer demand with a maximum degree of customization.

selecting supplier attributes for making decision on supplier selection (Weber et al., 1991; Chao et al., 1993; Briggs, 1994; Wei et al., 1997; Ghodsypour and O'Brien, 1998; Petroni and Braglia, 2000; Lamming, 1993; Lamming et al., 2000). It can be seen that the supplier/partner selection process should not only consider price, but also a wide range of factors such as quality, organization and culture, with a view of decision making by considering the whole supplier/partner capability in a long-term and strategic way. This long-term expectation developed between the manufacturer and supplier(s) can provide the opportunity for improving performance. To recognize a supplier in a long-term partnership, the measurement of supplier organization is needed. It should be analyzed quantitatively, such that far-seeing customer and supplier relationships can be evaluated. The literature and practice has seen the growth of customer and supplier relationships from a focus on operational purchasing relationships to strategic partners and boundary evaporation. 3.1 Various techniques in supplier/partner selection Obviously the selection of supplier plays a key role in an organization because the cost of raw material constitutes the main cost of a final product. Selecting the right suppliers significantly reduces the purchasing cost and improves corporate competitiveness. There are various techniques for selecting suppliers/partners, such as mathematical techniques. A comprehensive review of these articles, which have addressed the problem, can be found in Ghodsypour and O'Brien (2001), which include techniques like:

3 Suitability of adopting CBR technique in supplier selection

Under the issue of supplier/partner selection, a lot of articles have addressed the importance of
Figure 1 Enterprise applications architecture

88

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

. . . . .

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

linear programming; mixed integer-programming approach; goal programming techniques; multi-objective programming; and non-linear programming.

Figure 2 The CBR cycle

Besides mathematical techniques, other artificial intelligent (AI) techniques were used in developing decision support systems for partner/supplier selection (Gupta and Nagi, 1995; Herrmann and Minis, 1996; Minis et al., 1999). However, it is noticed that although the above approaches can solve the supplier/partner selection problems, however, the complexity of the system is not suitable for enterprises to solve the issue efficiently without high capability in advanced computer programmers. Actually, most small and medium sized enterprises (SMEs) could not afford these complex mathematical and sophisticated intelligent approaches. As a result, case based reasoning (CBR), an applicable user-friendly artificial intelligent technique, which can be used in providing the advanced supplier selection function with high compatibility under the need of managing supplier relationship, is needed (for details, see Choy and Lee, 2002a, b). 3.2 Case-based reasoning (CBR) Case-based reasoning is a problem solving technique in which past cases and experiences are re-used to find a solution to particular problems. The central tasks involved in CBR methods are to: . identify the current problem situation; . find a past case similar to the new one; . use that case to suggest a solution to the current problem; . evaluate the proposed solution; and . update the system by learning from this experience (see Figure 2). Aamodt and Plaza (1994) described CBR as a cyclical process comprising the four ``Re''s: (1) Retrieve the most similar case(s). (2) Reuse the case(s) to attempt to solve the problem. (3) Revise the proposed solution if necessary. (4) Retain the solution as part of a new case. Figure 2 illustrates the process involved in CBR represented by a schematic cycle. It is shown that a new problem is matched against historical 89

cases in the case base using heuristically cased indexed retrieval methods with one or more similar cases being retrieved. A solution suggested by the matching cases is then reused and tested for success. At this stage, if the best-retrieved case is a perfect match, then the system has achieved its goal and finishes. However it is more usual that the retrieved case matches the problem case only to a certain degree. In this situation, the closest case may provide a sub-optimal solution or the closest retrieved case may be revised using some pre-defined adaptation formulae or rules. Adaptation in CBR systems means that such systems have a rudimentary learning capability, which can improve or become more discriminatory, as the number of cases increases. Nevertheless, while adaptation is useful in many situations, it is by no means essential as in the case of supplier selection. Many of the most successful commercial CBR systems do not perform adaptation at all. They either simply reuse the solution suggested by the best matching case or they leave adaptation to people (Watson, 1997). Besides the applications in the areas of planning (Kolodner, 1993), diagnosis (Watson and Abdullah, 1994), design (Perera and Watson, 1995), process control (Koegst et al., 1999), there is a growing trend for enterprises to apply CBR technology in the make or buy decision making process (Mclvor and Humphreys, 2000). It has become clear that CBR is useful in searching knowledge,

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

helping users in comparing various tasks and items, automatically notifying users with relevant new knowledge update, and so on (Dutta et al., 1997; Choy and Lee, 2000; 2001). In summary, it can be seen that the application of CBR technique in the areas of SRM such as supplier evaluation/selection is a new approach, which can be used in integrating with CRM through the process of new product development and supply chain management. Since CBR is an advanced reasoning technique simulating human reasoning to retrieve a relative case, modify it and find a solution for the new coming problem, it can be used to supplement the conventional measures, which mainly rely on experts such as the purchasing manager or procurement engineer, to make a decision on outsourcing matters.

market using the CBR technique to manage and sort potential suppliers to form customer-supplier integration strategies. The CBR engine, in which a case-base decision tree is constructed, arranges past practices in a systematical way for the retrieval process. In the case base module, each case includes the name of a case, a case description, a recommended solution and the further reference linkages such as the inter-link between the updated files or the front page on the Internet of the target supplier. In order to implement the concept of the customer-supplier relationship management, the database in the form of a case base is built on a Web site for collecting the opinions from the customers. The two CBR modules in ISRMS responsible for matching the customer demand with the respective supplier capability for a particular product are the supplier selection module (CSSM) and the help desk module. 4.1 Case-based supplier selection module (CSSM) A built-in supplier selection workflow is programmed in the case base engine such that an authorized supplier list is stored, consisting of three profiles: technical capability, quality assessment and organization profile (Choy and Lee, 2002a). Data of each supplier are stored in a case structure, each consisting of a number of fields representing the criteria in each category. The cases in ISRMS show the relevant numerical performance values of the correspondent criteria of suppliers. During the supplier selection process, an external supplier list is converted to the format of a case and is then imported to the case base of the authorized supplier list when either the case retrieval is exhaustive or new potential suppliers are desired in sourcing (Choy and Lee, 2002b; 2003). The nearest neighbour technique is used in CSSM, in which the similarity of the problem (target) case to a case in the case-library for each case attribute is determined. This measure is multiplied by a weighting factor. Then the sum of the similarity of all attributes, called similarity ratio, is calculated to provide a measure of the similarity of that case in the library to the target case. This can be represented by eq. (1) (Kolodner, 1993): 90

4 Intelligent supplier relationship management system (ISRMS)

ISRMS proposed in this paper is used by the organization to master its core competence by means of subcontracting operations that cannot be used in building up the knowledge inside the organization. ISRMS uses one of the applications of CBR technology, which belongs to the classification task integrating CRM with SRM to provide the prediction and assessment of supplier capability. The architecture of the ISRMS is shown in Figure 3. It is divided into front end and back end. In the front end, ISRMS is linked with the company's local and overseas customers such as wholesalers and retailers to acquire their information related to the products. The back end of ISRMS consists of a case-base data warehouse containing cases stored in various departments within the company's local and overseas offices as well as in other plants. Moreover, the CBR engine which use the stored cases for problem solving is also installed in the back end. By doing so, CRM and SRM functions are linked up by the front and back end of ISRMS. The intelligent (AI) computational tool, the CBR engine, embedded inside ISRMS is a new concept since there are no similar systems in the

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

Figure 3 Architecture of ISRMS

Pn

i1

wi simfiI ; fiR Pn ; i1 wi

Figure 4 Information flow of CSSM

where wi = weight of feature I; sim = similarity function; fiI fiR = the values of feature fi in the input. Finally, in order to facilitate the operations of ISRMS, the CBR engine analyzes the product data collected from the Web site such that supplier performance according to customer feedback is transformed to the requirements into organization when selecting appropriate suppliers in the business. This approach enables the transfer of customer demand to the related suppliers directly. 4.1.1 Design the decision tree of CSSM In outsourcing manufacturing, it is important to have a database system such that suppliers' performance can be directly related to the subcontracted parts. The design of CSSM is for the purpose of linking the company's supplier rating system (SRS) with the product coding system (PCS). By doing so, past practices of the suppliers are stored with respect to their subcontracted parts. The information flow of CSSM is shown in Figure 4: 91

Supplier rating system. It is the core of the CSSM; the main purpose of which is to rate a supplier's performance level according to the pre-defined criteria. Product coding system. It categorizes parts and components of a product. For a company who outsourced significantly, it is essential to have a good product coding system because of the benefits of classification as well as traceability.

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

The combination of these two systems forms the mechanism of supplier evaluation and thus helps a company to search the most suitable suppliers or a list of supplier attributes that fulfills the requirement of the new product or order. A five-tier decision tree is constructed in the generic CSSM, which is shown in Figure 5. The selected supplier attributes of the supplier rating system (SRS) are divided into the first and second tier of the generic system, based on the classification of the supplier performance. The number of attributes in Tiers 1 and 2 are adjustable, according to the actual policy in different companies, to suit company strategies. In Tiers 3 and 4, a general and detail categorized company product coding system (PCS) is designed. This function is to sort the potential suppliers into the right product category. In Tier 5, suppliers are classified into high and low, representing preferred and accepted suppliers respectively, according to

Figure 5 Mechanism of constructing the generic CSSM

the resulting scores. For CSSM to function successfully, five steps are carried out: (1) Based on the requirement of each company, determine the primary supplier selection attributes, e.g. delivery, quality, etc. and take them from the attribute library into Tier 1. (2) Select the secondary attributes from the library and link them to the primary attributes. (3) Evaluate the company's product coding system; divide them into different material categories such as plastic, mechanical parts, and accessories. The coding system is grouped in the form of a bill of materials (BOM). Finally, a weight is added to each attribute. (4) List all the outsourced material codes for the purposes of linking potential suppliers (according to the score they got from the selection process). (5) Divide the score point into two classes; low score (one to five points) and high score (six to ten points). The purpose of this classification is to speed up the retrieval process of preferred and accepted suppliers, as well as to maintain the case base thus formed easily. By following these five steps, a logical hierarchy decision tree for CSSM to function accurately is built (Choy et al., 2003). 4.2 Help desk module A help desk module, which is independent from the CSSM, is responsible for validating the accuracy level of the solutions from the supplier selection process. With reference to Figure 3, while the selection of the potential suppliers is the duty of CSSM to analyze the criteria of potential suppliers, it is the merit of using the CBR help desk module to measure and benchmark the accuracy level of the selection. It is done by means of comparing the supplier's attributes in the new supplier with those from the suppliers sorted from the past practices. Moreover, three types of supplier performance reports are stored in Excel report format in the help desk module, acting as the key performance indicator (KPI) for monitoring the suppliers' performance. They include: 92

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

(1) time delivery reports; (2) inventory level reports; and (3) defective items reports. Similar to CSSM, the reasoning technique of the help desk module relied on the comparisons of the similarity ratios in the performance measurements of potential suppliers. The process in the help desk module is divided into three steps. First, the system developer makes use of the CBR software package to build a case base; where each case contains numbers of records in the past practices. Second, after arranging all cases in a systematic way on a decision tree, end users such as the senior management personnel start to use the user interface to retrieve past practices. The user needs to input the part number in the space provided, and hence answers the questions searched by the engine. Finally, the appropriate suppliers will be ranked automatically according to the answers given by the user. The three KPI reports are also retrieved for performance benchmarking purposes. As a result, the selected supplier retrieved by the help desk module is the best past practice, which has been used as the best practice in the process of benchmarking potential suppliers proposed by Choy et al. (2002). The score acts as a reference when comparing with the potential supplier selected from the supplier selection process.

budget, through the collaborative product commerce via global networking with their strategic suppliers and customers for operational excellence. ISRMS can help to select appropriate suppliers to develop new products according to customer demand received from the global network through its embedded CRM module. 5.1 ISRMS in supplier selection When applying ISRMS for the identification of preferred suppliers, the database of the customer relationship management (CRM) is divided into six different attributes, namely the technical support, customer service, product price, product quality, product package and customer satisfaction, to form a category of customer information database shown in Figure 6. All the information of the past practices is stored in the case base in the form of cases containing the weightings of these six attributes. They will be used for selecting suppliers/partners using the embedded CBR engine when new product development is required. In practice, after collecting the right information from customers through the Web into these six categories, the data are summarized into key elements, which the company can transfer into a form of performance measurement criteria for selecting appropriate suppliers in the sourcing process. In the database for the supplier relationship management (SRM), as shown in Figure 7, each supplier is assigned a special score in each criterion. Customers, who are normally referred to key wholesalers and retailers, send in the product requirement through the CRM module. Information collected in the customer information database is then correlated to the
Figure 6 Categories of customer information database in the CRM module

5 Application case study and results

ISRMS was applied with the intention of strengthening the supplier relationship management function in Honeywell Consumer Products (Hong Kong) Limited. Honeywell is a multi-national based manufacturer of consumer products such as fans, heaters, humidifiers, air cleaners, etc. Its office is in Hong Kong and the main manufacturing plant in Shenzhen, mainland China. Honeywell employs around 2,800 workers and staff, 2,500 are located at the Shenzhen office and 300 at the Hong Kong office. Honeywell has around 50 core suppliers and over 2,000 potential suppliers for sourcing. Its vision is to build up a knowledge-based learning organization, which can produce quality and innovative products with enhanced services to their customers on time within 93

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

Figure 7 Supplier selection criteria of the supplier rating system in the SRM module

potential suppliers and sequentially goes through the help desk module using question and answer approach to validate the resulting suppliers with those in the supplier list. The mechanism in parallel will result in a list of suggested suppliers. By doing so, ISRMS provides an analytical result to help managers to make the right decision rather than relying only on the original past practices or on human reasoning. 5.2 Implementation of ISRMS Before implementing ISRMS in Honeywell, some preparation steps were: . to set up a ``support'' link on the front page of the company Web site, which is used in collecting the customer information; . to distribute all the information into suitable categories; and . to group the supplier natures, supplier code, and supplier history records into a single database. After finishing these preparations, Honeywell started to install ISRMS into its existing supplier management system. ISRMS embeds a CBR software package called Case-Advisor to retrieve the supplier information into Honeywell's server. The core structure of the CBR engine is the Case-Advisor. Case-Advisor is traded by Sententia Software Company at Simon Frazier University, Canada. It is a CBR software package modelled on a standard technique where humans and used in problem solving. This technique is to recall past experiences, or ``cases'', that are similar to the current situation and adapt them to meet the needs of the new situation. Case-Advisor is divided into three main components, namely, Case Authoring (CA), Problem Resolution (PR) and Domain Manager (DM).

supplier selection criteria in CSSM of the SRM module to aid the corresponding manager to make a decision on selecting the appropriate suppliers. As shown in Figure 8, for example, customer satisfaction is related to quality, shipment quality, delivery, and product price, while product package is linked with the shipment quality and product price. Indeed, the correlation, which is updated from time to time, mainly depends on the emphasis customers expressed in the information. Clear classification is necessary to ensure that the supplier selection process fulfills the requirements demanded from the key customers in order to retain good relationship. When using ISRMS, Honeywell first sets its supplier requirements in the form of a list of performance criteria with target scores; it forms a ``new'' problem. The new problem is then entered into CSSM's CBR cycle for generating

Figure 8 Relationship between the CRM and SRM's information database

94

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

CA is used in constructing the case base while PR is used in finding the potential solution. The following information is usually input in the two modules for the CBR engine to function: (1) In case authoring module: . Case or supplier name. . Case description, which includes: the existing supplier code; the business nature (e.g. plastic, mechanical, electronic parts manufacturers, etc.); and the major type of suppliers. (2) In problem resolution module: . Case solution, which includes: the score points of each criterion; and the establishment of a link to the past practices. Finally, the name of the material categories, which acts as a medium in linking the different tiers of hierarchy tree to form the case base of the CSSM in searching for the appropriate suppliers is input. The Domain Manager (DM) is an interface to case-bases that integrates with ODBC databases such as Oracle, Sybase, Microsoft SQL server, Microsoft Excel and Access, etc. DM performs several functions like create, copy, and rename, etc. of the domain case base list, which are used in the Case-Advisor. By linking the CRM and SRM database through the Domain Manager using the Case Authoring and Problem Resolution Modules, the customer requirement can be linked with suppliers' capability in real time base. 5.3 Illustration example air cleaner plastic cover ISRMS has been tested in Honeywell to validate the feasibility of this system in an actual industrial environment. In total four steps are involved in building the case base and the application in the Authoring Module and the Problem Resolution Module of ISRMS respectively. In the Case-Advisor Authoring Module, three steps are required. In the following example, the searching of preferable suppliers is carried out for the plastic cover. Construction of the decision tree In the beginning, a decision tree is constructed by using Case-Advisor to represent the company's product coding system (Tier 3, 95

Tier 4) as well as the supplier rating system (Tier 1, Tier 2). In Figure 9, the computerized decision tree shows the integration of SRS with the plastic group's PCS to retrieve the classified potential plastic suppliers from the case base. A schematic flow chart is also shown on the left to illustrate the logic behind the decision tree. Honeywell based on four kinds of supplier performance information to estimate the value of the performance score of each supplier in order to input into the supplier rating system. They are: (1) The frequency of delivery delay. (2) Quotation price of each transaction. (3) The frequency of defective rework. (4) Number of customer compliant. After evaluating these reports, a score is given to each supplier, which represents the level of satisfaction by Honeywell. The purpose of constructing CSSM for selecting preferred suppliers, which is made by constructing a decision tree and a case base, is to integrate the existing suppliers' past practices with Honeywell's product coding system. This approach is a new concept, which contributes to the operations of manufacturers who outsource significantly in business. The hierarchy of the decision tree in the core CBR structure is illustrated in Figure 9, showing the integration of SRS and PCS in the 5-Tier CSSM. All potential suppliers inside an organization are arranged into particular groups according to their score points in each of the supplier attributes contained in the supplier selection criteria category. In the air cleaner project, the score points are divided into two classes, the first class contains marks from one to five, regarded as low performance; and the other class is from six to ten, regarded as high performance. The reasons dividing scores into two classes are in twofold. First, this helps the system to retrieve suppliers in an efficient and accurate way. Second, this can minimize the complexity in the maintenance of ISRMS. The construction of the decision tree is crucial due to the fact that the accuracy in the retrieval stage is mainly dependent on the allocation of suppliers in the appropriate class. In summary an existing supplier performance database is transformed into performance case base in the form of cases rather than idle data,

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

Figure 9 Construction of the decision tree

which can be utilized for potential supplier evaluation purposes. Building the content of the case After building the decision tree, it is necessary to build the content into the case. The content in the Case Authoring module containing the Honeywell's supplier list is shown in Figure 10. It involves the case name, description, and solution. In addition, the case base can be linked to a particular file in the format such as the Word document (.doc), Excel spreadsheet
Figure 10 Building the content of the case

(.xls), or the front page of the suppliers' Web site. As the retrieval technique used by Case Advisor belongs to the nearest neighbor one, it allowed the case name, contents inside the description or solution appearing in the form of the searching character. In the Honeywell case shown in Figure 10, three parameters are input into the space. (1) Case name. This is usually the supplier/company name, which is used in linking Tier 2 with Tier 4.

96

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

(2) Description. The information related to the nature of the company and the types of supply are input in this column. (3) Solution. The primary (Tier 1) and secondary (Tier 2) performance criteria as well as the weighting for each criterion are input in this column. For the button ``case options'', it links with different supplier performance information or the past practices of the concerned supplier, for instance, the four type of information mentioned in (1) above. Hence, the case contains different past practice data from various departments such as: . quotation price from the marketing department; and . defective record from the quality assurance department. By entering the required data with corresponding score, suppliers' performance records from different department are consolidated. Connecting the case with the related questions This step is to build up the interrelationships between cases and questions so as to build the decision tree for the CBR cycle. As shown in Figure 11, the case base consisted of two sections: one is a pool of cases in the case list,
Figure 11 Connecting the case with the related questions

and the other is a pool of questions in a question list. They are separately built and there is no interrelationship between the cases and the question list. The way to link the case and the question list affects the accuracy of the retrieval steps as the CBR cycle relies on the logic built in the decision tree. In CSSM, they are simply linked by dragging and dropping the question to the particular case. In practice, one question can be interlinked with a number of cases, whereas a dialog box will be shown at the end of the connection. Moreover, a case can be linked with more than one question if it is necessary. By this connection, a case network is formed in the case base within a short period of time. After completing the above three steps, the required case base is built. In fact the building of this case base for Honeywell is only required once in the beginning stage. Lastly, one step is required in the Problem Resolution Module to find the solution. Finding solutions When a user wants to search for the supplier for supplying the air cleaner cover, the Problem Resolution Module is used. As illustrated in Figure 12, the keywords of the problem description for searching potential suppliers for the air cleaner cover are input in the case base on

97

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

Figure 12 Finding solution by the problem resolution module

the space provided in the left upper corner. They can be the material name, product code or criteria. After entering the keywords, the CBR engine starts to retrieve appropriate suppliers by using the nearest neighbor technique. A question list is shown in the ``questions'' area where the users select and answer those that are relevant to the task. The rank of the suppliers change until it reaches the final answer according to the questions provided. The detail information of the most appropriate supplier is shown on the right screen when double clicking the appropriate supplier. The supplier thus found is then compared with those from the help desk module, which compares this supplier's performance with those from past practices, using the supplier performance reports of shipment schedule, inventory level and defective items stored in Excel format as the key performance indicator (KPI). The supplier thus recommended is the most suitable one.

6 Results and benefits

After implementing ISRMS for the selection of potential suppliers in various projects, the performance results are compared with those using the experience-based approach, as shown in Table I. 98

As shown in Table I, it is indicated that the adoption of ISRMS contributes significantly to the Honeywell (Hong Kong) plant. Moreover, by using the case-based nature of CSSM and the help desk module, suppliers' performance can be monitored effectively through retrieving the suppliers' past records, which forms part of the case base. Consequently, the chance of selecting the right suppliers/partners is increased resulting in the production of more reliable products. This can be shown by the significant decrease in the percentages of delay in delivery, quality below standard and customer claims as shown in Table II. Since 90 per cent on time delivery was achieved after using ISRMS, Honeywell's satisfactory rate reached 90 per cent. Moreover, shipment records revealed that late delivery of goods decreased to 10 per cent. According to the defective items report in Table I, the level of quality below standard decreased from 30 per cent to 15 per cent. Finally, reports from the customer service department showed that customer claims also decreased by 7 per cent. All these showed a great improvement in Honeywell's performance due to the right selection of preferred/accepted suppliers. As Honeywell is a multi-national manufacturer, its suppliers and business partners number thousands. The usage of

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

Table I The relationship between suppliers' and Honeywell's performance in pre- and post-implementation of ISRMS Performance of the ``plastic" suppliers Shipment schedule Pre-implementation of ISRMS (by experience) A delay of two weeks on average Post-implementation of ISRMS Operations improvement by Honeywell

Inventory level Defective items

Required by Honeywell, up to 20 per cent of the total requirement Defects can reach 30 per cent

A total of 90 per cent on-time delivery Reduce the chance of delay in delivery by 90 per frequently occurs cent through the use of urgent air freight to its end customers due to suppliers' delay in shipment Vendor managed inventory (VMI) is Cost saved by 20 per cent of the total requirement made possible Within 15 per cent Quality improved by 50 per cent

Table II Supplier selection performance by human and by ISRMS By Human (%) Honeywell satisfactory rate Delay in delivery Quality below standard Customer claims 65 20 30 25 By ISRMS (%) 90 10 15 18 Honeywell expected (%) 99 10 15 10

ISRM to handle highly structured supplier cases enables purchasing managers, engineers, and buyers to investigate different scenarios with finite supplier cases effectively. This is due to the system's ability to combine with a ``what-if'' analysis and the actionable knowledge obtained from the case-base in the case advisor. The speed of sourcing the capable, preferred or potential suppliers and decision making in the related attributes is increased. Consequently, quicker reaction in supplier selection and management occurs, providing a shorter new product development cycle time to be achieved. Cost reduction becomes possible accordingly. The other benefit is that the major part of ISRMS records the knowledge of workflow and can be fully implemented into the CRM module with little human involvement. This can solve the problem of losing supplier selection knowledge should any experienced key staff leave the corporation. In fact, new staff can allocate preferred suppliers easily by the help of the user-friendly help desk module in ISRMS. Lastly, those suppliers' past performance records, which were stored inactively in the company's database system, can be linked and used as active performance measurement system and supplier evaluation criteria. In summary, ISRMS records corporate knowledge in the supplier case-base, its algorithm and workflow to support the CRM functions. 99

7 Conclusions
While CRM focused on leveraging and exploiting the interaction with the customer to maximize customer satisfaction, ensure return business, and ultimately enhance customer profitability, SRM involved the management of preferred suppliers and finding new ones whilst reducing costs, making procurement predictable and repeatable, pooling buyer experience and extracting the benefits of supplier partnership. It becomes crucial for manufacturers to integrate the demand of customers to their preferred suppliers as well as sourcing new ones in a real time base during the new product development cycle in order to remain competitive in business. By using ISRMS to link customer demand with suppliers' capability, preferred suppliers are selected. CSSM is designed to integrate the supplier rating system (SRS) with product coding system (PCS), with the objective of setting up a relationship between supplier performances and a company's product code. With the aid of the help desk module, which retrieves past practices and performance records of suppliers, it is possible for purchasing and sourcing managers to determine the level of subcontracting the task to these suppliers, especially when early supplier involvement is expected in the new product development process. This cannot be achieved satisfactorily by experience.

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

The major function of ISRMS is to integrate customer requirements on product quality, delivery time, and manufacturing cost by an advanced computational retrieval technology case-based reasoning (CBR) to evaluate suppliers through a single software platform. With the implementation of ISRMS, an organization can shorten the workflow of selecting business suppliers after receiving a new order. In addition, the potential suppliers retrieved from the CBR engine is supported by a similarity ratio. The workflow of the new system minimizes human reasoning in the system, which enhances the consistency of the mechanism of the system. The ISRMS platform helps manufacturers to reduce the total production time and time to market. By the help of ISRMS, enterprises can easily implement the customer relationship management (CRM) strategy in each department, to establish a close relationship with suppliers/partners by the integration with the supplier relationship management (SRM) strategy, and consequently increase the manufacturers' own competitiveness, reputation and revenue in the market. In conclusion, by applying ISRMS in Honeywell, the main goals of CRM and SRM, which are to build long term and profitable relationship with chosen customers and to maximize the value of a manufacturers' supply base by increasing flexibility and responsiveness to customer requirements and substantially faster cycle times, are achieved.

References
Aamodt, A. and Plaza, E. (1994), ``Case-based reasoning: foundational issues, methodological variations, and system approaches'', AICom Artificial Intelligence Communications, Vol. 7 No. 1, pp. 39-59. Briggs, P. (1994), ``Case study: vendor assessment for partners in supply'', European Journal of Purchasing and Supply Management, Vol. 1 No. 1, pp. 49-59. Chao, C., Scheuing, E.E. and Ruch, W.A. (1993), ``Purchasing performance evaluation: an investigation of different perspectives'', International Journal of Purchasing and Materials Management, Summer, Vol. 29 No. 3, pp. 33-9. Choy, K.L. and Lee, W.B. (2000), ``Task allocation using case-based reasoning for distributed manufacturing systems'', Logistics Information Management, Vol. 13 No. 3, pp. 167-76.

Choy, K.L. and Lee, W.B. (2001), ``Multi-agent based virtual enterprise supply chain network for order management'', Journal of Industrial Engineering Research, Vol. 2 No. 2, pp. 126-41. Choy, K.L. and Lee, W.B. (2002a), ``A generic tool for the selection and management of supplier relationships in an outsourced manufacturing environment the application of case based reasoning'', Logistics Information Management, Vol. 15 No. 4, pp. 235-53. Choy, K.L. and Lee, W.B. (2002b), ``On the development of a case-based supplier management tool for multi-national manufacturers'', Measuring Business Excellence, Vol. 6 No. 1, pp. 15-22. Choy, K.L. and Lee, W.B. (2003), ``A generic supplier management tool for outsourcing manufacturing'', Supply Chain Management, An International Journal, Vol. 8 No. 2 pp. 140-54. Choy, K.L., Lee, W.B. and Lo, V. (2002), ``An intelligent supplier management tool for benchmarking suppliers in outsource manufacturing'', International Journal of Expert Systems with Applications, Vol. 22 No. 3, pp. 213-24. Choy, K.L., Lee, W.B. and Lo, V. (2003), ``Design of an intelligent supplier relationship management system a hybrid case-based neural network approach'', International Journal of Expert Systems with Applications, Vol. 24 No. 3, pp. 225-37. Dutta, S., Wierenga, B. and Dalebout, A. (1997), ``Case-based reasoning systems: from automation to decision-aiding and simulation'', IEEE Transactions on Knowledge and Data Engineering, Vol. 9 No. 6, November/December. Ghodsypour, S.H. and O'Brien, C. (1998), ``A decision support system for supplier selection using an integrated analytic hierarchy process and linear programming'', International Journal of Production Economics, Vol. 56-57, pp. 199-212. Ghodsypour, S.H. and O'Brien, C. (2001), ``The total cost of logistics in supplier selection, under conditions of multiple sourcing, multiple criteria and capacity constraint``, International Journal of Production Economics, Vol. 73, pp. 15-27. Gupta, P. and Nagi, R. (1995), ``Flexible optimization framework for partner selection in agile manufacturing'', IERC Proceedings 1995, 4th Annual Industrial Engineering Research Conference, Norcross, GA, pp. 691-700. Herrmann, J.W. and Hodgson, B. (2001), ``SRM: leveraging the supply base for competitive advantage'', Proceedings of the SMTA International Conference, October, Chicago, IL. Herrmann, J.W. and Minis, I.V. (1996), Design Evaluation and Partner Selection for Agile Manufacturing, Institute for Systems Research and Department of Mechanical Engineering, University of Maryland, College Park, MD. Koegst, M., Schneider, J., Bergmann, R. and Vollrath, I. (1999), ``IP retrieval by solving constraint satisfaction problems'', in FDL '99, 2nd International Forum on Design Languages, 30 August-3 September, Ecole Normale Superieure de Lyon, Lyon.

100

Case based intelligent supplier relationship management system

King L. Choy, Wing Bun Lee and Victor Lo

Supply Chain Management: An International Journal Volume 9 . Number 1 . 2004 . 86-101

Kolodner, J. (1993), Case-based Reasoning, Morgan Kaufmann, San Mateo, CA. Lamming, R.C. (1993), Beyond Partnership: Strategies for Innovation and Lean Supply, Prentice-Hall, Hemel Hempstead. Lamming, R.C., Johnsen, T., Zheng, J. and Harland, C. (2000), ``An initial classification of supply networks'', International Journal of Operations & Production Management, Vol. 20 No. 6, pp. 675-91. Mclvor, R.T. and Humphreys, P.K. (2000), ``A case-based reasoning approach to the make or buy decision'', Integrated Manufacturing Systems, Vol. 11 No. 5, pp. 295-310. Minis, I., Herrmann, J.W., Lam, G. and Lin, E. (1999), ``A generative approach for concurrent manufacturability evaluation and subcontractor selection'', Journal of Manufacturing Systems, Vol. 18 No. 6, pp. 383-95. Perera, R.S. and Watson, I. (1995), ``A case-based design approach for the integration of design and estimating'', in Watson, I. (Ed.), Progress in Case-Based Reasoning, Lecture Notes in Artificial Intelligence 1020, Springer-Verlag, Berlin.

Petroni, A. and Braglia, M. (2000), ``Vendor selection using principal component analysis'', Journal of Supply Chain Management, Vol. 36 No. 2, Spring, pp. 63-9. Shaw, R. (1999), ``CRM definitions defining customer relationship marketing and management'', in Customer Relationship Management: The Ultimate Guide to the Efficient Use of CRM, edited by SCN Education BV, HOTT Guide, 2001, available at: www.hottguide.com Watson, I. (1997), Applying Case-based Reasoning: Techniques for Enterprise Systems, Morgan Kaufmann, San Francisco, CA. Watson, I.D. and Abdullah, S. (1994), ``Developing case-based reasoning systems: a case study in diagnosing building defects'', in Proceedings of the IEE Colloquium on Case-Based Reasoning: Prospects for Applications, Digest No: 1994/057, 1/1-1/3. Weber, C., Current, J. and Benton, W. (1991), ``Vendor selection criteria and methods'', European Journal of Operational Research, Vol. 50 No. 1, pp. 2-18. Wei, S., Zhang, J. and Li, Z. (1997), ``A supplier-selecting system using a neural network'', IEEE International Conference on Intelligent Processing Systems, October, Bejing.

101