International Journal of Information Technology & Decision Making

Many times, benefit-opportunity-cost-risk (BOCR) information system (IS)-related decisions are based mainly on short-term financial variables. We propose a broader decision-making framework, using contingency theory to identify environmental specific factors and assimilation theory to identify post-implementation factors to be considered in the decision. This approach is demonstrated within the context of a case study: the decision to merge the City of Pittsburgh and Allegheny County IS functions using an analytic network process (ANP)/BOCR analysis. ANP is a multi-criteria decision-making approach toward making decisions taking into account multiple criteria, alternatives and their interrelationships. The contingency/assimilation approach proposed here can be used in all sorts of IS decisions while the proposed IS merge decision model can be applied, with some contextual modifications, to similar public IS merge decisions. In addition, the ANP/BOCR approach is meticulously explained to serve as a useful reference for prospective users.

The measurement of volatility is of fundamental importance in finance. Standard market practice adopted for volatility estimation from option prices leads to a considerable loss of information and the introduction of an element of arbitrariness in the volatility index computation. We propose to adopt fuzzy regression methods in order to include all the available information from option prices, and to obtain an informative volatility index. In fact, the obtained fuzzy volatility indices not only offer a most possible value, but also a lower and an upper bound for the interval of possible values, providing investors with an additional source of information. We also propose a defuzzification procedure to select a representative value within this interval. Moreover, we investigate the occurrence of truncation and discretization errors in volatility index computation by adopting an interpolation-extrapolation method. We also test the forecasting power of each volatility index on future realized volatility.

Analytic Hierarchy Process (AHP) is one of the most favorable decision tools for dealing with complex decision-making problems. Probabilistic linguistic term set (PLTS) is an up-to-date tool to deal with uncertain information in the decision-making process. In this paper, we extend the AHP to the probabilistic linguistic environment for perfecting the modeling ability of AHP in various decision-making problems. In order to apply the PLTSs to the AHP properly, we first redefine the probabilistic linguistic comparison matrix (PLCM) and propose a new consistency index. Then, we propose a new approach to check and improve the consistency of the PLCMs. After that, we aggregate the individual PLCMs into the collective PLCM and derive the priorities of the collective PLCM. Finally, we combine the priorities with the decision matrix to complete the ranking of alternatives, and a case concerning the performance assessments of three new areas is given and the comparative analysis about the results is performed to demonstrate the feasibility of the proposed method.

The problem of nonperforming loans is one of the biggest problems in the banking sector. In order to mitigate this problem, it is necessary to improve the methods of credit risk assessment. One way to minimize credit risk is to improve the assessment of the creditworthiness of the applicant. In order to make a more accurate assessment, many models have been developed using classification techniques. This paper demonstrates the use of classification techniques in the form of a single classifier or in a classifier ensemble setting. We proposed bagging as a model ensemble using artificial neural networks. In the experiment conducted with the Bosnian commercial banks dataset, the proposed model showed promising results according to evaluation criteria, especially after the process of feature selection. Both individual and wrapper feature selection methods were used. Bagging with neural network (NNBag) outperforms commonly used techniques with accuracy improvement from 1% to 5%. The superiority of the proposed model (NNBag) is confirmed on two widely available datasets for assessing creditworthiness. Based on experimental results on three datasets, it is proven that NNBag is suitable for use in the assessment of the creditworthiness of applicants.

The different web mining methods and techniques can help to solve some typical issues of the contemporary websites, contribute to more effective personalization, improve a website structure and reorganize its web pages. However, only several papers tried to combine web structure and web usage mining (WUM) methods with this aim. The paper researches if and how the combination of selected web structure and WUM methods can identify misplaced web pages and how they can contribute to improving the website structure. The paper analyzes the relationship between the estimated importance of the web page from the web page creator’s point of view using the web structure mining method based on PageRank and visitors’ real perception of the importance of that individual web page using the WUM method based on sequence patterns analysis, which eliminates the problem with repeated visits of the same web page during one session. The results prove that the expected probability of accesses to the individual web page correlates with the observed visit rate obtained from the log files using the WUM method. Furthermore, the website can be improved based on the consequent application of the residual analysis on the obtained results. The applicability of the proposed combination of the web structure and WUM methods is presented on two case studies from different application domains of the contemporary web. As a result, the web pages, which are underestimated or overestimated by the web page creators, are successfully identified in both cases.

Supply chain partner selection (SCPS) is an important issue for firms to remain highly competitive. SCPS is generally formulated as a fuzzy multi-criteria decision-making problem, of which the most crucial step is how to cope with the fuzzy correlations of multi-criteria and individual differences of experts. To gain more exact results, we adopt interval-valued intuitionistic fuzzy sets to express the fuzziness of multi-criteria. Fuzzy Choquet integral model is developed to explain correlations of multi-criteria and calculate the evaluation results of each expert. An improved Dempster–Shafer theory is utilized to reconcile differences and synthesize each expert decision results. Additionally, an example is presented to illustrate the potential application of the proposed method.

ABC analysis is a widespread classification technique designed to manage inventory items in an effective way by relaxing controls on low valued items and applying more rigorous controls on high valued items. In the literature, many classification models issued from different methodologies such as Mathematical Programming (MP), Metaheuristics, Artificial Intelligence (AI) and Multicriteria Decision Making (MCDM) are proposed to perform the ABC inventory classification. To the best of our knowledge, the cross-fertilization of classification models issued from different methodologies is rarely tackled in the literature. This paper proposes some hybrid classification models based on both Genetic Algorithm (Metaheuristics) and two MCDM methods (Weighted Sum (WS) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS)) to carry out the ABC inventory classification. To test the performance of the proposed classification models with respect to some existing models, a benchmark dataset from a Hospital Respiratory Therapy Unit (HRTU) is used. The computational results show that our proposed models outperformed the existing classification models according to some inventory performance measures. An additional performance analysis has also shown the effectiveness of our proposed models in inventory management.

Identifying the best solutions to large infrastructure decisions is a context-dependent multi-dimensional multi-stakeholder challenge in which competing objectives must be identified and trade-offs made. Our aim is to identify and explore features in an interactive visualization tool to help make group decision analysis more participatory, transparent, and comprehensible. We extended the interactive visualization tool ValueCharts to create Group ValueCharts. The new tool was introduced in two real-world scenarios in which stakeholders were in the midst of wrestling with decisions about infrastructure investment. We modeled the alternatives under consideration, for both scenarios, using prescribed criteria identified by domain experts. Participants in both groups were given instructions on how to use the tool to represent their preferences. Preferences for all participants were then displayed and discussed. The discussions were audio-recorded and the participants were surveyed to evaluate usability. The results indicate that participants felt the tool improved group interaction and information exchange and made the discussion more participatory. They expressed that visualizing individual preferences improved the ability to analyze decision outcomes based on everyone’s preferences. Additionally, the participants strongly concurred that the tool revealed disagreements and agreements and helped identify sticking points. These results suggest that a group decision tool that allows group members to input their individual preferences and then collectively probe into any differences makes the process of decision-making more participatory, transparent, and comprehensible and increases the quality and quantity of information exchange.

This paper describes the emergency rescue vehicle transportation network within the entire rescue period, and imitates rescue vehicle to select rescue route and to allocate emergency resource. The presented emergency rescue vehicle dispatch model seeks to minimize rescue time as the first objective function, minimize delay cost as the second objective function and maximize lifesaving utility as the last objective function in disaster response operations. To solve the proposed multiple objective model, a hybrid algorithm named nondominated sorting genetic algorithm (NSGA-II) with ant colony algorithm and a NSGA-II with random crossover and mutation, which can find better initial solution, are presented. In order to further prove the validity of the model and algorithm, a more complicated case is cited. Computational results are reported to illustrate the performance of the proposed model and algorithm. Statistical analysis confirms that the proposed random crossover and mutation operator outperforms the original crossover and mutation operator. The sensitivity analysis proves which parameter is more important for objective function values.

In-stream big data processing is an important part of big data processing. Proactive decision support systems can predict future system states and execute some actions to avoid unwanted states. In this paper, we propose a proactive decision support system for online event streams. Based on Complex Event Processing (CEP) technology, this method uses structure varying dynamic Bayesian network to predict future events and system states. Different Bayesian network structures are learned and used according to different event context. A networked distributed Markov decision processes model with predicting states is proposed as sequential decision making model. A Q-learning method is investigated for this model to find optimal joint policy. The experimental evaluations show that this method works well for congestion control in transportation system.

Since smartphones have become the most prevalent communication tool in the world, a wide variety of low-end to high-end smartphone products are currently available on the market. Choosing a suitable product becomes a challenge due to the problem of feature fatigue. This study developed a smartphone selection procedure for prospective users by incorporating ELECTRE-III method with Kano two-dimensional quality model. An empirical example of 15 smartphones from three different categories, namely, flagship, screen size and price, demonstrated that the credibility matrix of the revised ELECTRE-III had fewer extreme values (0 and 1) than its original counterpart. It was able to clearly distinguish the relative satisfaction of each option in the respective group, particularly for the tied products which could not be discerned by the original ELECTRE-III.