International Journal of Information Technology & Decision Making

Real-world decision-making problems often consist in considering multiple and antithetic objectives. Therefore, multi-objective decision making (MODM) is a practical framework in implicational areas. In this paper, a fuzzy MODM problem is considered, where all of its parameters are defined fuzzily, and a solution inspired by multi-attribute VIKOR method is proposed. The proposed method tries to find fuzzy efficient solution for a problem by minimizing its combinational distance from an ideal and anti-ideal solution. This method can reveal the efficient frontier of the problem. Applicability of the proposed method is shown in an illustrative example and its application is summarized in an investment problem. Both examples show applicability of the proposed method.

This paper presents a multicriteria approach to the evaluation of information technology (IT) projects. In this paper, we present the steps of the model to evaluate IT project investments, including the identification of IT project investment, the construction of IT investment or IT project categories, the assessment of the importance of criteria and establishes final recommendations. The methodology proposes a framework, based on multicriteria analysis, that describes the importance of classifying and prioritizing IT projects investments before taking decisions. Decisions on IT investments should consider the different characteristics of each IT project and in each case evaluate the tangible and intangible benefits. However, measurements of intangible benefits are usually subjective and require a formal procedure to minimize the difficulty and consequence of this. Thus, the model enables us to handle this subjectiveness and it is exemplified with a numerical illustration, the data being drawn from a preview study.

The rapid growth of the World Wide Web has resulted in intricate Web sites, demanding enhanced user skills to find the required information and more sophisticated tools that are able to generate apt recommendations. Markov Chains have been widely used to generate next-page recommendations; however, accuracy of such models is limited. Herein, we propose the novel Semantic Variable Length Markov Chain Model (SVLMC) that combines the fields of Web Usage Mining and Semantic Web by enriching the Markov transition probability matrix with rich semantic information extracted from Web pages. We show that the method is able to enhance the prediction accuracy relatively to usage-based higher order Markov models and to semantic higher order Markov models based on ontology of concepts. In addition, the proposed model is able to handle the problem of ambiguous predictions. An extensive experimental evaluation was conducted on two real-world data sets and on one partially generated data set. The results show that the proposed model is able to achieve 15–20% better accuracy than the usage-based Markov model, 8–15% better than the semantic ontology Markov model and 7–12% better than semantic-pruned Selective Markov Model. In summary, the SVLMC is the first work proposing the integration of a rich set of detailed semantic information into higher order Web usage Markov models and experimental results reveal that the inclusion of detailed semantic data enhances the prediction ability of Markov models.

This study used dynamic data envelopment analysis (dynamic DEA) to evaluate the operating performance of life insurance companies in Taiwan and China. In addition, this study adopted panel data regression, which employs the cross-section and time-series approaches, to investigate the impact of intellectual capital (IC) on operating performance. The results indicated that the overall performance of life insurance companies in China was better than that of life insurance companies in Taiwan. Furthermore, in both countries, the performance of life insurance companies with local capital was better than that of companies with foreign capital. The results also showed that human capital (HC) and structural capital (SC) had impacts on the operating performance of life insurance companies. The potential applications and strengths of DEA in assessing the life insurance industries in Taiwan and China are highlighted.

The primary purpose of our paper is to evaluate environmental performance as well as to model some nonseparable inputs and outputs using the data envelopment analysis (DEA) model. The efficiency analysis takes emission quota into consideration with the objectives of minimizing both total undesirable emissions and consumption of input resources. The value of emission quota that directly influences the environmental performance is obtained. The proposed model is applied to the data of power industries in 30 Chinese provinces. In addition, the sensitivity of the efficiency with respect to the value of emission quota is investigated. The results show the environmental protection in the power industry can be further improved. Our conclusion is that strict environmental regulations often enhance economic development rather than hinder it. This strongly suggests the government needs to pay more attention to pollution abatement because of its promoting effects on environmental performance.

This paper focuses on identifying relatively efficient configurations of algorithmic operators among a set of configurations in the development of heuristics or meta-heuristics. Each configuration is considered as a decision-making unit with multiple inputs and outputs. Then, data envelopment analysis (DEA) is adopted to evaluate relative and cross-efficiencies of a set of algorithmic configurations. The proposed approach differs from existing methods based on statistical tests in that multiple inputs and outputs are simultaneously considered in an integrated framework for the evaluation of algorithmic efficiency. A case study is presented to demonstrate the application of DEA for determining the efficient configurations of genetic algorithm operators. The evaluation results of two DEA models are also compared. The DEA evaluation results are consistent with those obtained by a commonly used statistical method.

This paper deals with the problem of multicriteria clusters construction. The aim is to propose a multicriteria clustering procedure aiming at discovering data structures from a multicriteria perspective by defining a dissimilarity measure which takes into account the multicriteria nature of the problem. Comparing two objects in the multicriteria context is based on the preference information that expresses whether these objects are indifferent, incomparable or one is preferred to the other. The proposed approach uses this preference information with an agreement–disagreement similarity index to compute a dissimilarity measure. The approach generates, according to the preference relations, a set of clusterings. Each clustering expresses a way of grouping objects according to the preference relation used. A good quality final clustering is obtained by combining the clusterings generated previously using a clustering ensemble technique.

The rapidly growing online social networks have generated great expectations connected with their potential business values. The aim of this paper is to identify the active valuable nodes that can spread business information to a large fraction of the individuals in large-scale temporal online social networks as quickly as possible. Most studies focus on static social networks, the study on the identification of active valuable nodes in temporal online social networks with quantitative attributes is still young. In this paper, we propose a method to identify active valuable nodes based on their static structural properties and temporal behavioral attributes. The method first chooses the candidates of the active valuable nodes by the static analysis of their structural properties. Then, the candidate's behavioral trend is extracted from its activity records. Through analyzing the spatio-temporal characteristics of the behavioral trend, the method distinguishes active valuable nodes from inactive ones and reveals typical evolutionary processes. We perform experiments on two practical online social networks with thousands of nodes. The experimental results demonstrate that the method can identify the active valuable nodes for information diffusion in large-scale temporal online social networks accurately and efficiently. It would be useful for business applications.

Degree centrality is considered to be one of the most basic measures of social network analysis, which has been used extensively in diverse research domains for measuring network positions of actors in respect of the connections with their immediate neighbors. In network analysis, it emphasizes the number of connections that an actor has with others. However, it does not accommodate the value of the duration of relations with other actors in a network; and, therefore, this traditional degree centrality approach regards only the presence or absence of links. Here, we introduce a time-variant approach to the degree centrality measure — time scale degree centrality (TSDC), which considers both presence and duration of links among actors within a network. We illustrate the difference between traditional and TSDC measure by applying these two approaches to explore the impact of degree attributes of a patient-physician network evolving during patient hospitalization periods on the hospital length of stay (LOS) both at a macro- and a micro-level. At a macro-level, both the traditional and time-scale approaches to degree centrality can explain the relationship between the degree attribute of the patient-physician network and LOS. However, at a micro-level or small cluster level, TSDC provides better explanation while the traditional degree centrality approach is found to be inadequate in explaining its relationship with LOS. Our proposed TSDC measure can explore time-variant relations that evolve among actors in a given social network.