A comparative analysis of machine learning systems for measuring the impact of knowledge management practices

Decision Support Systems 54 (2013) 1150–1160

Contents lists available at SciVerse ScienceDirect

Decision Support Systems journal homepage: www.elsevier.com/locate/dss

A comparative analysis of machine learning systems for measuring the impact of knowledge management practices Dursun Delen a,⁎, Halil Zaim b, Cemil Kuzey c, Selim Zaim d a

Department of Management Science and Information Systems, Spears School of Business, Oklahoma State University, United States Department of Management, Fatih University, Buyukcekmece, Istanbul, 34500, Turkey Department of Management, Fatih University, Buyukcekmece, Istanbul, 34500, Turkey d Department of Mechanical Engineering, Marmara University, Goztepe, Istanbul, 34722, Turkey b c

a r t i c l e

i n f o

Article history: Received 29 May 2012 Received in revised form 20 September 2012 Accepted 28 October 2012 Available online 1 November 2012 Keywords: Knowledge management Machine learning Predictive modeling Service industry Impact analysis

a b s t r a c t Knowledge management (KM) has recently emerged as a discrete area in the study of organizations and frequently cited as an antecedent of organizational performance. This study aims at investigating the impact of KM practices on organizational performance of small and medium-sized enterprises (SME) in service industry. Four popular machine learning techniques (i.e., neural networks, support vector machines, decision trees and logistic regression) along with statistical factor analysis (EFA and CFA) are used to developed predictive and explanatory models. The data for this study is obtained from 277 SMEs operating in the service industry within the greater metropolitan area of Istanbul in Turkey. The analyses indicated that there is a strong and positive relationship between the implementation level of KM practices and organizational performance related to KM. The paper summarizes the finding of the study and provides managerial implications to improve the organizational performance of SMEs through effective implementation of KM practices. © 2012 Elsevier B.V. All rights reserved.

1. Introduction As one of the contemporary management tools, knowledge management (KM) has been increasing in popularity of the tools/techniques used by large organizations and multinational companies to gain sustainable competitive advantage in the long run. Despite the growing interest and implementation initiatives, the concept of KM is still evolving, and to date there is no unifying or overarching theoretical framework that has been widely accepted. While KM has been frequently cited as an antecedent of organizational performance, there is a paucity of empirical research regarding the impact of KM practices on organizational performance. This lack of interest is even more pronounced in the context of small and medium-sized enterprises (SMEs). While implementation of KM practices in large size firms provides immense business opportunities in terms of achieving cost efficiency and gaining competitive advantage, there is less evidence of small- and medium-sized enterprises (SMEs) implementing KM practices to capture similar benefits. The question then remains open “how well KM practices fit with the SMEs”, which form the largest group of business establishments in both developed and emerging market economies from the viewpoint of generating employment and economic growth [12]. They account for more than half of the employment and value added contributions in most countries [50]. Similar trend is also ⁎ Corresponding author. Tel.: +1 918 594 8283; fax: +1 918 594 8281. E-mail addresses: [email protected] (D. Delen), [email protected] (H. Zaim), [email protected] (C. Kuzey), [email protected] (S. Zaim). 0167-9236/$ – see front matter © 2012 Elsevier B.V. All rights reserved. http://dx.doi.org/10.1016/j.dss.2012.10.040

observed in Turkey where SMEs constitute more than 90% of the total number of businesses and employ 61% of the workforce [53]. In view of the fact that the success of SMEs has a direct impact on the national economy, this study aims to provide two main contributions to SME research. First, based on a sample of SMEs operating in two sub-sectors of textile industry within the greater metropolitan area of Istanbul in Turkey, this study aims to examine the impact of KM practices on the organizational performance of SMEs. Second, the machine learning approach, which has been gaining growing interest in business research, is employed to identify the most important KM practices on organizational performance of SMEs. The remainder of the paper is organized as follows. The next section provides a rather comprehensive review of the relevant literature on KM practices. Research methodology is presented in Section 3. Data analysis, results and their implications are provided in Section 4. The paper concludes with Section 5 where a summary of the findings along with future research directions are given. 2. Literature review The field of KM has recently emerged as a new area of interest for both academic and business circles. The review of the recent literature reveals an increasing number of studies covering many different facets of KM [38]. Along with this growing interest, researchers proposed a large number of definitions of KM, most of which overlapping on common characteristics [33], while each emphasizing on a few distinct aspects of KM. Generally speaking, the existing studies in

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

the field of KM have largely focused on three major streams [17]: the philosophical nature of KM; the processes of knowledge management (i.e., generation, sharing and distribution of knowledge); and the infrastructure of knowledge management in terms of technology and effective management of knowledge and business practices. Zaim et al. [56] classify the infrastructure further into four areas: technology, organizational culture, organizational structure and intellectual capital. Similarly they also identify four areas of processes for KM: knowledge generation and development; knowledge codification and storage; knowledge transfer and sharing; and knowledge utilization. In the forthcoming section, we will develop the concept of KM in line with the categorization purported by Zaim et al. [56], and will subsume both KM processes and related Knowledge Management Infrastructure under the general heading of KM practices. 2.1. KM practices It has been argued that the effectiveness of KM depends on how the generation of new knowledge is organized and how existing knowledge is transferred throughout the organization. Recent studies have expressed considerable interest in knowledge sharing practices [24]. The benefits of knowledge transfer and sharing have also been discussed widely among the scholars and practitioners [48]. Therefore, one of the most important objectives of KM is to bring together intellectual resources and make them available across organizational boundaries. It has been suggested that organizations often waste their resources and lose a significant amount of money for repeating the same mistakes, duplicating projects and being unaware of each other's knowledge due to the lack of knowledge transfer and sharing throughout the organization [44]. Knowledge transfer is not a unidirectional movement. Effective knowledge transfer is more than the movement of knowledge from one location to another. Organizations can get significant learning experience through knowledge transfer between units and people. It tends to improve competency of both sides that transfer and share knowledge. It is because knowledge does not leave the owner when it has been transferred. As a result, the value of knowledge grows each time a transfer takes place and the key to value creation lies in how effective knowledge has been transferred throughout the organization. The role and importance of information and communication technologies in knowledge transfer have been emphasized by many scholars. Clearly, technological advances bring a vast number of new opportunities to transfer and share knowledge and expertise throughout the organization within departments, plants, countries and across national borders. These technologies have a strategic role in knowledge sharing specifically for the geographically dispersed global organizations [2]. The effective use of technologies creates new ways of knowledge transfer and hold promising solutions both in transfer of explicit knowledge and tacit knowledge — in terms of experience and expertise [26]. In this respect, it is often mentioned that technological infrastructure has a strategic importance in knowledge transfer not only within the organization but also among different organizations [57]. As a matter of fact, all healthy organizations generate knowledge. While they are interacting with their environment, they absorb information, combine it with their experiences, values and internal rules, turn it into knowledge, and take action based on it. Knowledge generation can be performed in many ways. The three of the main modes among others are knowledge acquisition, knowledge generation within the firm and collaborative knowledge generation. However, knowledge generation process is a set of activities for the conscious and intentional generation of knowledge under specific actions and initiatives firms undertake to increase their stock of corporate knowledge [10]. Knowledge generation process does not necessitate new knowledge generation. In many circumstances, organizations may prefer to acquire knowledge from other sources and adopt it for their own

1151

use [4]. Knowledge acquisition can be used for knowledge creation, and if it is novel and useful for the organization, also be considered as a part of knowledge generation. Organizations convert information they collect from internal and external sources into knowledge through their organizational learning process by combining it with their prior knowledge, experiences, values and organizational procedures [25]. Then, the knowledge becomes a part of their organizational knowledge base. This obviously explains why the knowledge acquired through these organizational processes is new and unique for that organization [29]. Knowledge is meaningful when it is codified, classified, put in a useful format and stored. Only then, it can be used by the right person, at the right time and in the right way. Knowledge codification and storage is important not only for an effective use of knowledge but also for reusability of knowledge in case it is needed so that the knowledge in question can be internalized to the organization rather than the knower [39]. Therefore, considering the organization's overall objectives and priorities, many studies have been concentrating on the classification and the codification of knowledge based on its types and purposes [32], and on the storage of knowledge to let the employees be able to access knowledge any time both at present and in the future. The codification of knowledge also enables to stock the knowledge resources and to assess the potential of the organization. The most challenging feature of knowledge codification is to extract it without losing its distinctive properties which makes it valuable [10]. Despite its importance, codifying and classifying knowledge is not that simple since it relies heavily on what people know. Thus, organizational knowledge is hard to capture, clarify and express perfectly fine considering the fact that it is dispersed and scattered throughout the organization. It is found in different locations, in peoples' minds, in various organizational processes, in corporate culture embedded into different artifacts and procedures and stored into different mediums such as print, disks and optical media [5]. There is a distinction between tacit and explicit knowledge in the storage of knowledge. Explicit knowledge can be easily collected, documented, stored and retrieved quite independently of any single individual through technological means and systems. On the other hand, tacit knowledge resides in the minds of the employees and seizes a great deal of an organization's knowledge resources [14]. If the organization's knowledge resources have been described as an iceberg, the explicit knowledge is the visible part of the iceberg above the surface, whereas the tacit knowledge includes the invisible part of the iceberg beneath the surface [23]. The codification of tacit knowledge unlike explicit ones is the most cumbersome activity in the overall process because of its subjective and situational nature, and it is intimately tied to the knower's experience. One of the most important and challenging aspects of KM is to enhance the development of a collaborative, trustworthy, emphatic and helpful organizational culture. The executives and scholars agree on the importance of a knowledge-friendly culture for the success of KM [21,45]. It is because knowledge is a context-dependent social concept [30] and a large part of organizational knowledge is embodied in social processes, institutional practices, traditions and values [6,15]. Therefore, no matter how powerful the tools and functions of KM are, it is of no use without willing participants and a supportive social and cultural environment [28]. While the cultural resistance is generally cited as one of the most important barriers to an effective implementation of KM [48], it is still contemplated as the neglected or underestimated side of KM practices. Therefore, it is strictly recommended for organizations to place a special emphasis on the social and cultural issues for the successful implementation of KM practices [5]. The appropriate organizational structure and guidelines as well as technical and non-technical expedients of which the organization has disposal constitute another building blocks of KM infrastructure [1]. Nonetheless, there is no single appropriate organizational structure for KM. Some scholars suggest a radical re-design for KM [35], while others

1152

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

think that it is not necessary. However, instead of highly centralized, control-based and rigid hierarchies, more flexible, decentralized and trust-based organizational structures with empowered workers are highly recommended in the KM literature [34,36]. One of the most important objectives of KM is to create value from organization's knowledge resources so that the knowledge held by the company can be transformed to fields of application and action [43]. This implies the effective and efficient knowledge utilization for the organization's competitive edge. For that reason, it has been argued that the success of KM practices mostly depends on how efficient and effective the knowledge has been used and the level of action based on it [52]. The KM literature clearly exposes that knowledge resources have been increasingly seen as an integral part of organizations' value creating processes. In a similar vein, companies have become aware of the importance of intellectual capital of their own [19]. Intellectual capital can be defined as ‘the sum of all the intellectual materials of a company’ – knowledge, information, intellectual property including trademarks, patents and licenses, experience and integrity, personnel competencies, collective brainpower, etc. – that is captured and leveraged to create value and that can be converted to wealth and profit [7,20,47]. Though there are a variety of different components that constitute intellectual capital, an increasingly popular classification divides intellectual assets into three categories: human capital, structural capital and customer capital [46]. 2.2. Performance The main objective of KM performance evaluation is to increase the effectiveness, efficiency and adaptability of KM efforts so as to add more value to the overall performance of the organization [49]. Given the general rule about performance evaluation that performance improves through evaluation, it is reasonable to argue that measuring the outcomes and evaluating the contribution of KM practices are important to ensure the sustainability and success of KM efforts over time. Without assembling the link between desired outcomes and KM practices continuously and demonstrating tangible or quantifiable intangible results, it is not possible for the top management to keep on investing and for the workers to preserve their concentration and motivation [31,41]. Apparently, evaluation of KM-related organizational performance also shows to what extent the intellectual resources of a firm have been utilized [16,37] as well as the degree of the conversion of the organizational knowledge into improved performance [27]. 3. Method What follows is a brief introduction to the machine learning techniques (i.e., artificial neural networks, support vector machines, decision trees and logistic regression) employed in this study as predictive modeling tools. These four techniques are selected based on their superior predictive performance and their popularity in the recently published research literature.

Artificial neural networks can be classified into several categories based on supervised and unsupervised learning methods and feed-forward and feedback recall architectures. A back propagation neural network (BPNN) uses a supervised learning method and feed-forward architecture. A BPNN is one of the most frequently utilized neural network techniques for classification and prediction [22]. The main appeal of neural networks is their flexibility in approximating a wide range of functional relationships between inputs and outputs. Indeed, sufficiently complex neural networks are able to approximate arbitrary functions arbitrarily well. One of the most interesting properties of neural networks is their ability to work and forecast even on the basis of incomplete, noisy, and fuzzy data. Furthermore, they do not require a priori hypothesis and do not impose any functional form between inputs and outputs. For this reason, neural networks are quite practical to use in the cases where knowledge of the functional form relating inputs and outputs is lacking, or when a prior assumption about such a relationship should be avoided. The success of the ANN models depends on properly selected parameters such as the number of nodes (neurons) and layers, the nonlinear function used in the nodes, learning algorithm, learning parameters (learning rate and momentum), initial weights of the inputs and layers, and the number of epochs (i.e., cycles) that the model is iterated. The structure of a typical ANN model consists of one input layer, one or more hidden layers and one output layer. A graphical depiction of the specific ANN model (i.e., multi-layered perceptron with one hidden layer) used in this study is shown in Fig. 1. In ANN methodology, the sample data often is divided into two main sub-samples which are named as training and test sets. During the training process, the neural network learns the relationship between output and input criteria, while in the testing process, test set is used to assess the true predictive performance of the model. 3.2. SVM (support vector machine) Support vector machine (SVM), originally developed by Vapnik [51], is among the most robust and accurate methods in data mining algorithms. Its theoretical foundation is derived from statistical learning theory. SVM combines the statistical methods and machine learning methods. SVM is a supervised learning method that generates input–output mapping functions from a set of training data. Basically SVM learns from observations. There is an input space and output space and a training set. The nature of the output space decides the learning type such as type of binary or multiple classification problems.

Input Layer

Hidden Layer

Output layer

OC KCS KU

HN1

3.1. Neural network KG

Artificial neural networks (ANNs) are analytic techniques modeled on the learning processes of the human cognitive system and the neurological functions of the brain. Recently, there has been a considerable interest in the development of artificial neural networks for solving a wide range of problems from a variety of fields. Neural networks are distributed information processing systems composed of many simple computational elements interacting across weighted connections. Inspired by the architecture of the human brain, neural networks exhibit certain features such as the ability to learn complex patterns of information and generalize the learned information. Neural networks are simply parameterized non-linear functions that can be fitted to data for prediction purposes.

HN2 OS TI

HN3

KTS IP

Fig. 1. Structure of the NN model.

PERF

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

In SVM, “attribute” is represented by predicted variable; “feature” is defined by transformed attribute. Hyperplane is defined by the transformed attribute. Also “feature selection” is known as the task of selecting the most appropriate representation. A set of features that describe one case is called a “vector”. SVM works by mapping data to a high dimensional feature space. The mapping functions can be either classification or regression function. SVM belongs to the type of maximal margin classifier. There are four kernel functions (linear function, polynomial function, radial based function, and sigmoid function) to be used in classification problems when the input data is not easily separable. To make the input data easily separable compared to the original data, the kernel functions are used to transform the input data to high dimensional feature space. The aim of SVM is to find the optimal hyperplane that separates the clusters of vector in such a way that cases with one category of the target variable on one side of the plane and cases with the other category are on the other side of the plane. The vectors near the hyperplane are the support vectors. A separator which is drawn as a hyperplane is found between the separated classes. The ultimate aim of SVM is to establish a maximal margin between the separated classes. This will be able to offer a good classification performance on the training data, and also provide high predictive accuracy for the future data from the same distribution. The characteristic of new data after separation can be used for prediction. Since SVM's learning ability is independent of the dimensionality of the future space, therefore SVM provides good performance [9].

methods assume that the residuals, or errors, must follow a normal distribution. If they are not the methods should not be used. Unlike ordinary linear regression, logistic regression does not assume that the dependent variable or the error terms are distributed normally. Also, it doesn't assume that the relationship between the independent variables and the dependent variable is linear. Logistic regression is a variation of ordinary regression which is used when the dependent variable is a categorical variable. Logistic regression also produces Odds Ratios (O.R.) associated with each predictor value. The “odds” of an event is defined as the probability of the outcome event occurring divided by the probability of the event not occurring. The Odds Ratio for a predictor is defined as the relative amount by which the odds of the outcome increase (O.R. greater than 1.0) or decrease (O.R. less than 1.0) when the value of the predictor variable is increased by 1.0 units. 4. Proposed methodology and its application The individual steps of the methodology used in this study are shown on Fig. 2. Principal purposes of this methodology are: (1) to

Step1 Develop the survey instruments (regarding the knowledge management criteria and organizational performance).

3.3. Decision tree (C5 algorithm) Decision trees are commonly used methods in data mining. The two main types of classification generated by decision trees are classification tree analysis and regression tree analysis. Decision trees are becoming increasingly popular methods of using data mining technique because decision trees are simple to understand and interpret, require little data preparation, handle numerical and categorical data and perform very well with large data set in a short time. Decision trees demonstrate excellent visualization of results and relationships [3]. Although there are many specific decision tree algorithms, the ID3, C4.5, C5.0, CART, and CHAID (Chi-squared Automatic Interaction Detector) algorithms, based on the recent data mining literature, are arguably the most popular ones. C5.0 is one of the most popular decision tree algorithms. Developed by Quinlan, C5.0 offers a number of improvements on its predecessors C4.5 and ID3. It is significantly faster than ID3, and is more memory efficient than C4.5. It creates considerably smaller decision tree while getting similar results to C4.5. It also supports boosting, which improves the trees and gives them more accuracy. C5.0 allows the weighting of different attributes and misclassification types. In addition, it automatically separates the data to help reduce noise. Boosting is part of the C5.0 decision tree algorithm as an integration technology, which is included to improve the accuracy of classification. C5.0 uses pre-pruning and post-pruning methods to establish the decision tree. C5.0 is a commercial and closed-source product [11,42]. It starts from the top level of the details to establish the decision tree. The set of training examples is partitioned into two or more subsets based on the outcome of a test in the value of a single attribute. The particular test is chosen by an information theoretic heuristic that generally gives close to optimal partitioning. This is repeated on each of the new subsets until a subset contains only examples of a single class, or the partitioning tree has reached a predetermined maximum depth. 3.4. Logistic regression Logistic regression is a generalization of linear regression. Regression analysis is a statistical tool for the investigation of relationships. Like the linear regression analysis, most of the usual statistical

1153

Step2 Select the survey sample,collect the data, examine and pre-process the data for completeness,consistency and accuracy.

Step3 Conduct an exploratory factor analysis (EFA)with verimax rotation to determine the underlying dimensions/constructs.

Step4 Test the constructs(identified in the previous step) for a good fit to the data using confirmatory factor analysis (CFA).

Step5 Develop and compare to each other predictive models to identify the best performing model.

Step6 Conduct sensitivity analysis on the best performing predictive models to identify the most important factors. Fig. 2. Steps of the study methodology.

1154

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

find the most appropriate method for accurately predicting the financial and non-financial performance; and (2) to identify the most important knowledge management criteria (by using the developed prediction models as the source of the relationship between inputs and outputs) that improve the financial and non-financial performance; and by using these prioritized factors, propose recommendations for the top management of the company in the service sector. Step 1: The survey instrument regarding knowledge management criteria and organizational performance was developed. Step 2: In the second stage, the sample is selected and data is collected, examined and pre-processed. Step 3: An exploratory factor analysis (EFA) with varimax rotation was employed to determine the underlying dimensions of knowledge management performance. Step 4: Knowledge management constructs were tested using confirmatory factor analysis (CFA) in order to determine if the extracted dimensions in step 4 offered a good fit to the data. Step 5: In this stage, the most popular classification methods such as artificial neural networks, decision trees, support vector machines and logistic regression techniques, are evaluated and the best performing model specifications are selected. Step 6: After selecting the best model based on their predictive accuracy mentioned above the most important knowledge management variables affecting the financial and non-financial performance in the service sector were determined. What follows is a number of sub-sections delineating the implementation of these six steps.

4.1. Step 1: development of the survey instrument Data were gathered via cross-sectional mail survey using a self-administered questionnaire that was essentially composed of questions related to KM practices and organizational performance. Respondents were asked to indicate the level of agreement based on five-point Likert scales ranging from 1 “strongly disagree” to 5 “strongly agree” on each of the items measuring eight aspects of KM practices, which include organizational structure (OS), technological infrastructure (TI), organizational culture (OC), intellectual capital (IC), knowledge generation (KG), knowledge codification and storage (KCS), knowledge transfer and sharing (KTS), and knowledge utilization (KU). Measures of organizational non-financial and financial performance were based on items derived from a number of previous studies using this variable [8,13,55]. The level of organizational performance measures was identified using judgmental measures based on managers' perceptions of how the organization performed on multiple indicators of organizational performance relative to its rivals based on a five-point scale, ranging from ‘much worse than rivals’ through ‘much better than rivals’. The non-financial performance indicators include: service quality as perceived by customer, market share gain over the last three years, reputation among major customer segments, capacity to develop a unique competitive profile, new product/service development, and market development. The financial performance constructs include the following indicators; revenue growth over the last three years, net profits, return to investment, profit to revenue ratio, and cash flow from operation. The original version of the questionnaire was in English. This questionnaire was translated into the local language (Turkish). The local version was back translated until a panel of experts agreed that the two versions were comparable. The questionnaire was pre-tested several times to ensure that the wording, format, and sequencing of questions were appropriate. As the percentage of missing

data was calculated to be relatively small, occasional missing data on variables was handled by replacing them with the mean value. 4.2. Step 2: data collection Privately-held service companies within the city of Istanbul in Turkey were selected as the sampling frame of this survey to investigate the most important knowledge management practices and to measure its effect on financial and non-financial performance. For centuries as being the largest city of Turkey, Istanbul has nearly one-fifth of the nationwide population and has been undisputedly the main industrial and trade center. Data for this study was collected based on a self-administered questionnaire that was distributed to the Chief Administrative Officers of privately-held service companies that includes finance, logistic, stationary sectors, within the city of Istanbul. Of the 1200 questionnaires posted, a total of 738 usable questionnaires were returned after one follow-up, comprising a response rate of 61.5%. The responses indicated that a majority of the respondents completing the questionnaire were in fact members of the top management. It was requested that the questionnaire be completed by a senior officer/executive in charge of HRM and KM practices. A test for non-response bias for the mail survey was also conducted by comparing the first wave of survey responses to the last wave of survey responses. The test results indicated no significant difference in the responses between early and late respondents (p > 0.1). Therefore, no response bias was evident. 4.3. Step 3: exploratory factor analysis (EFA) Exploratory factor analysis with varimax rotation was performed on the Knowledge Management Infrastructure criteria in order to extract the dimensions underlying the construct. The EFA of the 29 variables yielded five factors explaining 62.8% of the total variance. Based on the items loading on each factor, these factors were labeled as ‘technology’ (Factor 1), ‘leadership’ (Factor 2), ‘human capital’ (Factor 3), ‘organizational culture’ (Factor 4), and ‘organization structure’ (Factor 5). These items are shown in Table 1. The Cronbach alpha values of reliability for the underlying factors range from 0.72 to 0.92 suggesting satisfactory level of construct reliability [40]. Similarly, EFA was undertaken to produce a set of parsimonious distinct non-overlapping dimensions of Knowledge Management Processes from the full set of 33 items. The factor analysis produced 5 factors which explained 66.4% of the observed variance, as shown in Table 2. These factors were labeled as knowledge utilization (Factor 1), knowledge classification and coding (Factor 2), knowledge generation (Factor 3), formal knowledge sharing (Factor 4) and informal knowledge sharing (Factor 5). The Cronbach alpha values of reliability for the underlying factors range from 0.73 to 0.93 suggesting satisfactory level of construct reliability. 4.4. Step 4: confirmatory factor analysis (CFA) This stage is also known as testing the measurement model, where the constructs of Knowledge Management Infrastructure and Knowledge Management process are tested using the first order confirmatory factor model to assess construct validity using the method of maximum likelihood. The results consistently supported the factor structure for two constructs as discussed earlier in the EFA stage. The confirmatory factor analysis (CFA) technique is based on the comparison of variance-covariance matrix obtained from the sample to the one obtained from the model. The measurement model results are presented in Tables 3 and 4, respectively. The figures in Tables 3 and 4 exhibit the standardized regression weight between each manifest variable and its corresponding latent variable. It was found that all t-values in the CFA are statistically

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

1155

Table 1 EFA of the KM infrastructure. Variables

Factors 1

Information systems in our corporate are convenient for our needs. Information technology systems in our corporate are new and fast. Our corporation has an efficient information system to be used for KM strategies. Our corporation has adequate database systems. Our corporate adequately invests in IT. The internet and intranet have been effectively used in our corporate. KM systems in our corporate (e.g. software regarding information saving and retrieval, databases, and search engines) are user-friendly. Emailing systems have been effectively used in our corporate. Our managers encourage us to learn more about KM. Our managers are good representatives of KM implementers. Our managers are supportive in developing, using, and sharing the knowledge. Our managers support creating new ideas and brainstorming. Our managers support us in our knowledge management-related activities. Our managers possess the required experience and competency in terms of knowledge management (KM). In our corporation, top management weighs much importance on the KM. Managers and employees of our corporate are experienced in their jobs. Managers and employees of our corporate have enough technical knowledge in their domains. Employees of our corporate both at the personnel and management level possess the competence in terms of knowledge and personal features. Employees of our corporate are qualified at a satisfactory level in terms of their educational background. I can identify employees of our corporate as “highly qualified knowledge management individuals”. Our corporate conducts adequate number of training activities. Our corporate culture encourages teamwork. Our corporate culture supports the idea of cooperation and knowledge sharing. Our corporate culture encourages knowledge creation. We trust in our colleagues and managers. There exists an effective delegation of authority and the managers of each unit can make their own departmental decisions without consulting the top management. Without any hesitation, I can do my own initiative regarding my job within my authority. There is not a rigid chain of command between different levels of management. There are no problems in terms of establishing and sharing authority and responsibility.

2

3

4

5

0.82 0.80 0.78 0.75 0.75 0.74 0.67 0.59 0.76 0.74 0.73 0.73 0.73 0.72 0.63 0.78 0.78 0.75 0.72 0.66 0.44 0.76 0.74 0.62 0.53 0.72 0.71 0.61 0.46

Table 2 EFA of the KM process. Variables

Factors 1

Corporate knowledge is reflected in customer relationship processes. Corporate knowledge is reflected in our production and service systems. Our corporate has a management style which is convenient to practically make use of the accumulated knowledge. Our decision making processes are working efficiently. Our corporate has adopted the philosophy of “continuous learning” and practicing the lessons learned. The knowledge obtained through the training is implemented in a short while. Our corporate effectively makes use of its knowledge potential. I effectively make use of my knowledge/experience in the work environment. We have data storage and archiving system through which we can get rapid access to accurate information. All personnel of our corporate record the data and the information which is revealed by their operations. We have an effective record-storing system in which the related information about the products, services, employees, and customers is saved. Information about the products, services, employees, and customers is updated on a regular basis. Our duties and operations are well-identified and are recorded. All information about my job is regularly classified, filed, and stored in an electronic environment. I can quickly and easily obtain the information that I need. The information about our suppliers and competitors is saved and recorded up-to-date. Our corporate supports innovative thinking and encourages creating innovative ideas. All employees of our corporate are encouraged for continuous learning. Highly qualified and featured individuals are tried to be attracted to work in our corporate. Our corporate successfully implements a suggestion system. Brainstorming sessions are conducted for creating alternative solutions to problems and for system development (i.e. improving the current systems). Employees of our corporate actively contribute to the process of knowledge creation. Our corporate conducts enough number of R&D activities. I have access to new and updated information on the web. Our corporate is systematically devoted to create and develop knowledge. We pay special attention to share the accumulated knowledge with our colleagues. We improve our work processes by sharing our knowledge and experience with our colleagues. Teamwork is very helpful in sharing the knowledge. We efficiently make use of e-mailing and the Internet to share the knowledge. To achieve informal knowledge-sharing, we organize picnics, soccer games, and family visits with our friends and try to get together apart from the work environment. We conduct meetings with the other departments to coordinate the knowledge-sharing. There is a strong communication between the employees and the managers.

2

3

4

5

0.79 0.78 0.73 0.70 0.69 0.68 0.67 0.66 0.80 0.76 0.75 0.75 0.75 0.71 0.69 0.63 0.75 0.73 0.72 0.66 0.65 0.64 0.63 0.61 0.60 0.77 0.75 0.65 0.51 0.80 0.60 0.55

1156

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

Table 3 CFA of the KM infrastructure. Variables Technology Information systems in our corporate are convenient for our needs. Information technology systems in our corporate are new and fast. Our corporation has an efficient information system to be used for KM strategies. Our corporation has adequate database systems. Our corporate adequately invests in IT. The internet and intranet have been effectively used in our corporate. KM systems in our corporate (e.g. software regarding information saving and retrieval, databases, and search engines) are user-friendly. Emailing systems have been effectively used in our corporate. Leadership Our managers encourage us to learn more about KM. Our managers are good representatives of KM implementers. Our managers are supportive in developing, using, and sharing the knowledge. Our managers support creating new ideas and brainstorming. Our managers support us in our knowledge management-related activities. Our managers possess the required experience and competency in terms of knowledge management (KM). In our corporation, top management weighs much importance on the KM.

Regression weight

t-Value

0.89⁎ 0.81⁎ 0.73⁎ 0.68⁎ 0.80⁎ 0.64⁎ 0.73⁎

28.1 24.7 21.7 19.6 – 18.5 21.5

0.81⁎

16.3

0.77⁎ 0.76⁎ 0.79⁎ 0.72⁎ 0.72⁎ 0.73⁎ 0.67⁎

21.9 – 22.3 20.1 20.2 20.7 18.5

Human capital Managers and employees of our corporate are experienced in their jobs. Managers and employees of our corporate have enough technical knowledge in their domains. Employees of our corporate both at the personnel and management level possess the competence in terms of knowledge and personal features. Employees of our corporate are qualified at a satisfactory level in terms of their educational background. I can identify employees of our corporate as “highly qualified knowledge management individuals”. Our corporate conducts adequate number of training activities.

0.78⁎ 0.79⁎ 0.81⁎

16.7 16.9 17.4

0.66⁎ 0.63⁎ 0.43⁎

16.9 – 10.5

Organizational culture Our corporate culture encourages teamwork. Our corporate culture supports the idea of cooperation and knowledge sharing. Our corporate culture encourages knowledge creation. We trust in our colleagues and managers.

0.79⁎ 0.75⁎ 0.78⁎ 0.63⁎

24.9 – 19.9 16.2

0.44⁎

10.7

0.57⁎ 0.70⁎ 0.73⁎

13.8 16.6 –

Organizational structure There exists an effective delegation of authority and the managers of each unit can make their own departmental decisions without consulting the top management. Without any hesitation, I can do my own initiative regarding my job within my authority. There is not a rigid chain of command between different levels of management. There are no problems in terms of establishing and sharing authority and responsibility. – Fixed for estimation. ⁎ p b 0.01.

significant at 0.01 levels. It indicates that all the individual factor loadings to be highly significant, giving support to convergent validity. The goodness-of-fit indices for Knowledge Management Infrastructure and Knowledge Management process are demonstrated in Table 5. These indices conform to the normal acceptable standards. The values of χ 2 statistic were 1133 and 1615, with the values of χ 2/df ratio varying between 3.16 and 3.52 for the Knowledge Management Infrastructure and Knowledge Management process constructs respectively. This ratio should be within the range of 0–5 where lower values indicate a better fit. The results show that constructs do fit in with this criterion. In addition, the GFI, AGFI and CFI for the Knowledge Management Infrastructure and Knowledge Management process constructs are highly satisfactory, as they are very close to a value of 1.0, which denotes a perfect fit. The results attest the construct validity for the measurement models of Knowledge Management Infrastructure and Knowledge Management process.

4.5. Step 5: comparative analysis of predictive models In the study, total ten inputs and two outputs were employed. These ten inputs are ‘technology’, ‘leadership’, ‘human capital’, ‘organizational culture’, ‘organization structure’, ‘knowledge utilization’, ‘knowledge classification and coding’, ‘knowledge generation’, ‘formal knowledge sharing’ and ‘informal knowledge sharing’. Two outputs, ‘financial

performance’ and ‘non-financial performance’, are selected as binary variables. Average values for the financial and non-financial organization performance were used as a split criterion. The group with a performance score of above average value was rated as 1 and the group with the performance score of below average value was rated as 0. With this information, individual organization can be classified as successful and not successful. The performance of the models used in binary (two-group) is measured by using a confusion matrix which is given in Table 6. A confusion matrix contains valuable information about actual and predicted classifications created by the classification model. For the purposes of the study, we used well-known performance measures such as overall accuracy, AUC (Area Under the ROC Curve), Recall and F-measure. All of these measures for each model used in the study were evaluated, after which the models were compared on the basis of proposed performance measurements. For the SVM model, the linear, polynomial, sigmoid and RBF (Radial Basis Functions) kernel functions were tested. For the financial and non-financial performance models, SVM Linear function and SVM (RBF) function were selected respectively. The data set was partitioned into training and testing data sets. 70% of the data was used for training and 30% was used for testing. For performance analysis, the test data sets were used for assessment.

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

1157

Table 4 CFA of the KM process. Variables

Regression weight

t-Value

Knowledge utilization Corporate knowledge is reflected in customer relationship processes. Corporate knowledge is reflected in our production and service systems. Our corporate has a management style which is convenient to practically make use of the accumulated knowledge. Our decision making processes are working efficiently. Our corporate has adopted the philosophy of “continuous learning” and practicing the lessons learned. The knowledge obtained through the training is implemented in a short while. Our corporate effectively makes use of its knowledge potential. I effectively make use of my knowledge and experience in the work environment.

0.75⁎ 0.85⁎ 0.85⁎ 0.80⁎ 0.78⁎ 0.78⁎ 0.81⁎ 0.72⁎

25.3 26 26.2 24.4 – 23.4 24.6 21.2

0.79⁎ 0.81⁎ 0.77⁎

23 23.7 22.2

0.82⁎ 0.79⁎ 0.77⁎ 0.78⁎ 0.69⁎

24 22.9 – 26.9 19.6

Knowledge classification and coding We have data storage and archiving system through which we can get rapid access to accurate information. All personnel of our corporate record the data and the information which is revealed by their operations. We have an effective record-storing system in which the related information about the products, services, employees, and customers is saved. Information about the products, services, employees, and customers is updated on a regular basis. Our duties and operations are well-identified and are recorded. All information about my job is regularly classified, filed, and stored in an electronic environment. I can quickly and easily obtain the information that I need. The information about our suppliers and competitors is saved and recorded up-to-date. Knowledge generation Our corporate supports innovative thinking and encourages creating innovative ideas. All employees of our corporate are encouraged for continuous learning. Highly qualified and featured individuals are tried to be attracted to work in our corporate. Our corporate successfully implements a suggestion system. Brainstorming sessions are conducted for creating alternative solutions to problems and for system development (i.e. improving the current service and production systems). Employees of our corporate actively contribute to the process of knowledge creation. Our corporate conducts enough number of R&D activities. I have access to new and updated information on the web. Our corporate is systematically devoted to create and develop knowledge.

0.80⁎ 0.73⁎ 0.72⁎ 0.68⁎ 0.74⁎

22.3 20.2 19.5 18.6 24.7

0.75⁎ 0.56⁎ 0.70⁎ 0.77⁎

– 15 19.2 25.1

Formal knowledge sharing We pay special attention to share the accumulated knowledge with our colleagues. We improve our work processes by sharing our knowledge and experience with our colleagues. Teamwork is very helpful in sharing the knowledge. We efficiently make use of e-mailing and the Internet to share the knowledge.

0.77⁎ 0.73⁎ 0.82⁎ 0.61⁎

– 26.8 21.8 16.1

0.53⁎

13.3

0.72⁎ 0.84⁎

19.6 –

Informal knowledge sharing To achieve informal knowledge-sharing, we organize picnics, soccer games, and family visits with our friends and try to get together apart from the work environment. We conduct meetings with the other departments to coordinate the knowledge-sharing. There is a strong communication between the employees and the managers. – Fixed for estimation. ⁎ p b 0.01.

The Area Under the Curve (AUC) for the test data sets was used to compare the mode's predictive performances. According to the AUC, the SVM–RBF and SVM–Linear models demonstrated very good performance measurements, with the C5.0 decision tree being the best of all the presented models. 4.5.1. Overall accuracy (AC) Accuracy is known as the percentage of records that is correctly predicted by the model. It is defined as being the ratio of correctly predicted cases to the total number of cases.

Accuracy ¼

TP þ TN TP þ TN þ FP þ FN

ð1Þ

4.5.2. Precision Precision is defined as the ratio of the number of True Positive (correctly predicted cases) to the sum of the True Positive and False Positive. 4.5.3. Recall Recall is also known as the Sensitivity or True Positive rate. It is defined as the ratio of the True Positive (the number of correctly predicted cases) to the sum of the True Positive and the False Negative. 4.5.4. F-measure F-measures take the harmonic mean of the Precision and Recall Performance measures. Therefore, it takes into consideration both the Precision and the Recall as being important measurement tools for these calculations [3]. F‐measure ¼ 2 

Table 5 Goodness-of-fit statistics. Model/construct

χ2

χ2/df

RMR

GFI

AGFI

CFI

KM process KM infrastructure

1133 1625

3.16 3.62

0.06 0.055

0.91 0.89

0.88 0.86

0.94 0.93

Precision  Recall Precision þ Recall

ð2Þ

According to the overall accuracy rate, the SVM–Linear model outperforms three models in accuracy (AC), but not significantly. As a result of AC evaluation, it achieves a higher accuracy rate of 77.8%. SVM–RBF model accuracy rate is very close to SVM–Linear but it is

1158

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

Table 6 Confusion matrix for financial performance.

Predicted

Actual

Not Successful

Successful

Not Successful

True Negative

False Positive

Successful

False Negative

True Positive

not so significant. Following these models, the next best model that demonstrates a high accuracy rate is the C5.0 decision tree algorithm (77.4%). According to the overall accuracy rate, SVM–Linear outperforms three models in accuracy (AC) even if it is not significantly. SVM– Linear achieves the highest accuracy rate (77.8%). SVM–RBF accuracy rate is very close to SVM–Linear in terms of performance. In addition, the next best model that demonstrates high accuracy rate is the C5.0 decision tree algorithm (77.4%). In terms of precision (P), SVM–Linear model does outperform the other models significantly. SVM Linear achieves 80.2% precision rate which is significantly higher than the rest of the compared models. When the F-measure is considered, the C5.0 decision tree model outperforms the rest of the models (79.1%), while the SVM–Linear model achieves the second best F-measure rate (76.6%). Table 7 compares five models in considering test data set. The results indicated that SVM–Linear model outperformed the other models. On the other hand, considering the non-financial performance measurement, SVM (RBF) model performs best in terms of overall accuracy rate (82.4%) which is shown in Table 8. It outperforms all the available models. In addition to accuracy rate, SVM model has the highest area under curve (.88). When we look at recall performance measurement, SVM and logistic regression perform equally well. They both possess 82.3% in recall. Furthermore, SVM model outperforms three models in F-measure as well. It achieves the highest F-measure with 83.5%. Even if neural network performs the highest precision measurement with 84.9%, it is not significantly higher than SVM model's precision of 84.6%. In summary, SVM (RBF) model performs very well for non-financial performance.

4.6. Step 6: determining the most important KM variables As mentioned in the previous steps, SVM–Linear model has an acceptable capability of predicting the organizational financial

performance. The impact of KM dimensions on organizational financial performance was evaluated and ranked based on the same model. This also provides managers with invaluable information in identifying which KM practices they should concentrate in order to have a better organizational financial performance. Table 9 shows the contribution of KM practices to the organizational financial performance in terms of the degree of their importance levels and their respective rankings. From the full set of 10 KM practices, knowledge utilization (0.34) appears as a leading factor. Organizational Culture is the second most important criterion with the importance level of 0.237, while knowledge generation is found to be the third important KM practice with the importance level of 0.176. The fourth important KM practices is informal knowledge sharing. In contrast, human capital and organizational structure are the least important KM practices in terms of their effects on organizational financial performance. This finding is not particularly surprising that KM practices have been primarily focused on knowledge utilization and knowledge generation and informal sharing in service industry. Table 10 shows the most important KM dimensions on organizational non-financial performance. Similarly with the financial performance, it was discovered that knowledge utilization has been found to be the most important KM practices in terms of their effects on non-financial organizational performance. Organizational structure appeared to be the second important factor, which is also consistent with the existing KM literature. Similarly, knowledge generation was found to be the third important critical factor affecting the non-financial organization performance. Technological Infrastructure also featured as important though they had relatively less impact on non-financial performance.

5. Summary and conclusion There is a scant research attention which considers the knowledge management practices and non-financial performance and financial performance within the context of service industry. The main thrust of this study was to investigate and determine the most important knowledge management practices in terms of both financial and non-financial performance using machine learning tools. Exploratory and confirmatory factor analyses were employed to produce empirically verified and validated underlying dimensions of KM practice construct drawing on a sample of service sector. The findings of study indicated that knowledge utilization had a strong and positive effect on both non-financial and financial performance. Also a strong and positive relationship was noted between knowledge generation and non-financial performance and financial

Table 7 Prediction results for financial performance.

SVM (Linear) Decision tree (C5.0) Logistic regression Neural network

Accuracy (AC)

Sensitivity/True Positive rate or recall (TP)

False Positive rate (FP)

Specificity/True Negative rate (TN)

False Negative rate (FN)

Precision (P)

F measure

0.778 0.774 0.764 0.755

0.733 0.867 0.724 0.762

0.178 0.318 0.196 0.252

0.822 0.682 0.804 0.748

0.267 0.133 0.276 0.238

0.802 0.728 0.784 0.748

0.766 0.791 0.752 0.755

Table 8 Prediction results for non-financial performance.

SVM (RBF) C5.0 Logistic regression Neural network

Area Under the Curve (AUC)

Accuracy (AC)

Sensitivity/True Positive Rate or Recall (TP)

False Positive Rate (FP)

Specificity/True Negative rate (TN)

False Negative rate (FN)

Precision (P)

F measure

0.880 0.840 0.878 0.878

0.824 0.803 0.811 0.815

0.825 0.802 0.825 0.802

0.178 0.196 0.206 0.168

0.822 0.804 0.794 0.832

0.175 0.198 0.175 0.198

0.846 0.828 0.825 0.849

0.835 0.815 0.825 0.824

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

1159

limitations by sampling SMEs from other sectors and geographic regions to obtain a larger, more comprehensive sample data.

Table 9 Importance of KM practices on the organizational financial performance. KM practices

Importance level

Ranking

Knowledge utilization (KU) Organizational culture (OC) Knowledge generation (KG) Informal knowledge sharing Human capital Organizational structure (OS)

0.34 0.237 0.176 0.106 0.089 0.004

1 2 3 4 5 6

performance. Finally, the results provided empirical evidence that the organizational culture and organizational structure were found as important for financial performance and non-financial performance respectively. Third generation KM studies particularly concentrates on the possible effects of KM applications on organizational performance. Organizational performance on the other hand, has been analyzed from two stand points which are financial performance and non-financial performance. Many research findings suggest that the relationship between KM and non-financial organizational performance is more significant and direct than the relationship between KM and financial performance [18,54]. Our study also analyzed the effects of KM on financial and non-financial organizational performance. The research findings reveal that knowledge utilization appears to be the most important factor of KM in terms of its effects on both financial and non-financial performance. It is mainly because knowledge is valuable if only it is utilized. Hence, one of the most challenging dimensions of KM is how to leverage and utilize knowledge in accordance with organizational objectives and convert it into a valuable form in order to gain competitive advantage. In our research we also found that the effects of knowledge utilization are more significant in non-financial performance than financial performance which is also convenient with the findings. When we look at the effects of KM on organizations' financial performance, knowledge utilization and organizational culture are often found to be the most significant factors of KM followed by knowledge generation, informal knowledge sharing, and human capital. Organizational structure has ignorable effect on financial performance. As mentioned before knowledge utilization is also the most important factor of KM from the non-financial stand point as well. Furthermore, other important factors affecting the non-financial performance are organizational structure, knowledge generation, technological infrastructure, and knowledge classification and coding. The importance of organizational culture, informal knowledge sharing, and leadership is less in comparison to previous factors. As is the case in any research, there are a number of limitations of this study. The most important limitation of this study is that it comprises only one sector in a specific geographic area in Turkey. Furthermore, even though the sample size seems to be satisfactory, a larger number of participants would have made the study stronger. The future directions of this research will focus on mitigating these

Table 10 Importance of KM practices on the organizational non-financial performance. KM practices

Importance level

Ranking

Knowledge utilization Organizational structure Knowledge generation Technological infrastructure Knowledge classification and coding Organizational culture Informal knowledge sharing Leadership

0.477 0.133 0.122 0.099 0.062 0.04 0.039 0.028

1 2 3 4 5 6 7 8

References [1] R. Beijerse, Questions in knowledge management: defining and conceptualizing a phenomenon, Journal of Knowledge Management 3 (2) (1999) 94–110. [2] S. Bender, A. Fish, The transfer of knowledge and the retention of expertise: the continuing need for global assignments, Journal of Knowledge Management 4 (2) (2000) 125–135. [3] J.A.M. Berry, G. Linoff, Data Mining Techniques—For Marketing, Sales and Customer Support, Wiley Publishing, New York, 1997. [4] G. Bhatt, Organizing knowledge in the knowledge development cycle, Journal of Knowledge Management 4 (1) (2000) 15–26. [5] G. Bhatt, Knowledge management in organizations: examining the interactions between technologies, techniques, and people, Journal of Knowledge Management 5 (1) (2001) 68–75. [6] M. Boisot, Knowledge Assets, Oxford University Press, New York, 1998. [7] N. Bontis, W. Keow, S. Richardson, Intellectual capital and business performance in Malaysian industries, Journal of Intellectual Capital 1 (1) (2000) 85–100. [8] K.B. Boyd, Strategic planning and financial performance: a meta-analytic review, Journal of Management Studies 28 (1991) 353–374. [9] N. Cristianini, J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press, London, 2000. [10] T. Davenport, L. Prusak, Working Knowledge, Harvard Business School, Boston, MA, 1998. [11] D. Delen, A comparative analysis of machine learning techniques for student retention management, Decision Support Systems 49 (2010) 498–506. [12] M. Demirbag, S.C.L. Koh, E. Tatoglu, S. Zaim, TQM and market orientation's impact on SMEs' performance, Industrial Management & Data Systems 106 (8) (2006) 1206–1228. [13] G.G. Dess, R.B. Robinson Jr., Measuring organizational performance in the absence of objective measures: the case of the privately-held firm and conglomerate business unit, Strategic Management Journal 5 (1984) 265–273. [14] C. Drott, Personal knowledge, corporate information: the challenges for competitive intelligence, Business Horizons 44 (2) (2001) 31–37. [15] P.M. Fayard, Strategic communities for knowledge creation: a Western proposal for the Japanese concept of Ba, Journal of Knowledge Management 7 (5) (2003) 25–31. [16] S. Firer, M. Williams, Intellectual capital and traditional measures of corporate performance, Journal of Intellectual Capital 4 (3) (2003) 348–360. [17] E. Geisler, A typology of knowledge management: strategic groups and role behavior in organizations, Journal of Knowledge Management 11 (1) (2007) 84–96. [18] I. Goll, N.B. Johnson, A.A. Rasheed, Knowledge capability, strategic change, and firm performance: the moderating role of the environment, Management Decision 45 (2007) 161–179. [19] J. Guthrie, U. Johanson, P.N. Bukh, P. Sanchez, Intangibles and the transparent enterprise: new strands of knowledge, Journal of Intellectual Capital 4 (4) (2003) 429–440. [20] S. Harrison, P. Sullivan, Profiting from intellectual capital, Journal of Intellectual Capital 1 (1) (2000) 33–46. [21] S. Hauschild, T. Licht, W. Stein, “Creating a Knowledge Culture”, McKinsey Quarterly. accessed at www.mckinseyquarterly.com 2002. [22] S.O. Haykin, Neural Networks and Learning Machines, Prentice Hall, New Jersey, 2009. [23] T.H.O. Herrgard, Difficulties in diffusion of tacit knowledge in organizations, Journal of Intellectual Capital 1 (4) (2000) 357–365. [24] R. Hicks, R. Dattero, S. Galup, A metaphor for knowledge management: explicit islands in a tacit sea, Journal of Knowledge Management 11 (1) (2007) 5–16. [25] J. Hong, Structuring for organizational learning, The Learning Organization 6 (4) (1999) 173–185. [26] M. Jacop, G. Ebrahimpur, Experience vs. expertise, Journal of Intellectual Capital 2 (1) (2001) 74–88. [27] T. Kalling, Knowledge management and the occasional links with performance, Journal of Knowledge Management 7 (3) (2003) 67–81. [28] T. Koulopoulos, C. Frappaolo, Smart Things to Know About Knowledge Management, Capstone Publishing Limited, United Kingdom, 1999. [29] V.G. Krogh, J. Roos, Managing Knowledge, Sage, London, UK, 1996. [30] J.C. Lang, Managerial concerns in knowledge management, Journal of Knowledge Management 5 (1) (2001) 43–59. [31] S. Lee, Using data envelopment analysis and decision trees for efficiency analysis and recommendation of B2C controls, Decision Support Systems 49 (2010) 486–497. [32] C. Lueg, Information, knowledge and networked minds, Journal of Knowledge Management 5 (2) (2001) 151–159. [33] M. Lytras, A. Pouloudi, A. Poulymenakou, Knowledge management convergence — expanding learning frontiers, Journal of Knowledge Management 6 (1) (2002) 40–51. [34] R. Maier, T. Hadrich, Centralized versus peer-to-peer knowledge management systems, Knowledge and Process Management 13 (1) (2006) 47–61. [35] Y. Malhotra, Knowledge management for E-business performance: advancing information strategy to Internet time, in: Information Strategy: The Executives' Journal, Summer issue, 2000, pp. 8–16.

1160

D. Delen et al. / Decision Support Systems 54 (2013) 1150–1160

[36] Y. Malhotra, Integrating knowledge management technologies in organizational business processes: getting real time enterprises to deliver real business performance, Journal of Knowledge Management 9 (1) (2005) 7–28. [37] B. Marr, O. Gupta, S. Pike, G. Roos, Intellectual capital and knowledge management effectiveness, Management Decision 41 (8) (2003) 771–781. [38] R. McAdam, S. Mcreedy, A critical review of knowledge management models, The Learning Organization 6 (3) (1999) 91–100. [39] H. Nemati, Global knowledge management: exploring a framework for research, Journal of Global Information Technology Management 5 (3) (2002) 1–11. [40] J.C. Nunnally, Psychometric Theory, 2nd ed. McGraw-Hill, New York, 1978. [41] C. O'Dell, J. Grayson, If Only We Knew What We Know: The Transfer of Internal Knowledge and Best Practice, The Free Press, U.S.A., 1998. [42] D.L. Olson, D. Delen, Y. Meng, Comparative analysis of data mining methods for bankruptcy prediction, Decision Support Systems 52 (2012) 464–473. [43] C. Ordaz, M. Allez, F. Alcazar, P.M. Fernandez, R. Cabrera, Internal diversification strategies and the process of knowledge creation, Journal of Knowledge Management 8 (1) (2004) 77–93. [44] S. Robertson, A tale of knowledge-sharing systems, Journal of Knowledge Management 6 (3) (2002) 295–308. [45] D. Skyrme, Knowledge Networking, Butterworth-Heinemann, Oxford, 1999. [46] D. Skyrme, Measuring Intellectual Capital. accessed at www.skyrme.com2002. [47] T. Stewart, The Wealth of Knowledge: Intellectual Capital and the Twenty-First Century Organization, Doubleday, Random House Inc., U.S.A., 2001. [48] K.E. Sveiby, R. Simons, Collaborative climate and effectiveness of knowledge work — an empirical study, Journal of Knowledge Management 6 (5) (2002) 420–433. [49] K. Toften, S. Olsen, Export market information use, organizational knowledge and firm performance, International Marketing Review 20 (1) (2003) 95–110. [50] UNCTAD, Small- and Medium-sized Transnational Corporations, United Nations, New York, 1993. [51] V. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, New York, 1995. [52] P. Wilhelmij, R. Schmidt, Where does knowledge management add value, Journal of Intellectual Capital 1 (4) (2000) 366–380. [53] B. Yilmaz, Küçük ve orta büyüklükteki işletmelerin toplumda üstlendikleri roller bakımından analizi, Dış Ticaret Dergisi 9 (30) (2004) 141–179. [54] M. Zack, J. McKeen, S. Singh, Knowledge management and organizational performance: an exploratory analysis, Journal of Knowledge Management 13 (6) (2009) 392–409. [55] H. Zaim, Knowledge management implementation in IZGAZ, Journal of Economic and Social Research 8 (2006) 1–25. [56] H. Zaim, E. Tatoglu, S. Zaim, Performance of knowledge management practices: a causal analysis, Journal of Knowledge Management 11 (6) (2007) 54–67. [57] X. Zhao, J. Xie, The impact of information sharing and ordering co-ordination on supply chain performance, Supply Chain Management 7 (1) (2002) 24–40.

Dr. Dursun Delen is the William S. Spears Chair in Business Administration and Professor of Management Science and Information Systems in the Spears School of Business at Oklahoma State University (OSU). He received his Ph.D. in Industrial Engineering and Management from OSU in 1997. Prior to his appointment as an Assistant Professor at OSU in 2001, he worked for a privately-owned research and consultancy company, Knowledge Based Systems Inc., in College Station, Texas, as a research scientist for five years, during which he led a number of decision support and other information systems related research projects funded by federal agencies, including DoD, NASA, NIST and DOE. His research has appeared in major journals including Decision Support Systems, Decision Sciences, Communications of the ACM, Computers and Operations Research, Computers in Industry, Journal of Production Operations Management, Artificial Intelligence in Medicine, Expert Systems with Applications, among others. He recently published four books: Advanced Data Mining Techniques with Springer, 2008; Decision Support and Business Intelligence Systems with Prentice Hall, 2010; Business Intelligence: A Managerial Approach, with Prentice Hall, 2010; and Practical Text Mining and Statistical Analysis for Non-structured Text Data Applications, with Elsevier, 2012. He is often invited to national and international conferences for keynote addresses on topics related to Data/Text Mining, Business Intelligence, Decision Support Systems, and Knowledge Management. He served as the general co-chair for the 4th International Conference on Network Computing and Advanced Information Management (September 2–4, 2008 in Soul, South Korea), and regularly chairs tracks and mini-tracks at various information systems conferences. He is the associate editor-in-chief for International Journal of Experimental Algorithms, associate editor for International Journal of RF Technologies, and is on editorial boards of five other technical journals. His research and teaching interests are in data and text mining, decision support systems, knowledge management, business intelligence and enterprise modeling.

Dr. Halil Zaim obtained his Bachelor degree in Economics from Istanbul University. He also completed his Master and Ph.D. education in Labor Economics from the same university. He is an Associate Professor at Fatih University, Management Department and Director of Continuous Education Center of the University. Zaim has three published books, numerous national and international journal papers and congress proceedings. His current scholarly interest is on Human Resource Management, Knowledge Management, and Business Ethics. Zaim is married with two children.

Dr. Cemil Kuzey lectures at the Department of Management at Fatih University in Istanbul, Turkey, teaching Operation Research and Statistics for Social Sciences. He acquired his Ph.D. degree in Business Administration through the Department of Quantitative Analysis, Istanbul University, Turkey. Among his academic pursuits, he took several graduate courses at the Ontario Institute for Studies in Education, University of Toronto. His research interests are related to Operation Research, Data Mining, Predictive Modeling and Business Intelligence.

Dr. Selim Zaim has received his B.S. degree in Mechanical Engineering from Istanbul Technical University and his Ph.D. degree in Production and Operations Management from Istanbul University. He has been serving as a professor in the Faculty of Technology at Marmara University. He has published over 100 articles and papers in various journals and congress proceedings. His current scholarly interests focus on multivariate data analysis, supply chain management, data mining and multi-criteria decision making. He reviews papers for a variety of journals. He is a member of the Industrial Management and Development Associations and Quality Association in Turkey (KALDER).