Ebook: DSS 2.0 – Supporting Decision Making with New Technologies
Advances in technology have resulted in new and advanced methods to support decision-making. For example, artificial intelligence has enabled people to make better decisions through the use of Intelligent Decision Support Systems (DSS). Emerging research in DSS demonstrates that decision makers can operate in a more timely manner using real-time data, more accurately due to data mining and 'big data' methods, more strategically by considering a greater number of factors, more precisely and inclusively due to the availability of social networking data, and with a wider media reach with video and audio technology.
This book presents the proceedings of the IFIP TC8/Working Group 8.3 conference held at the Université Pierre et Marie Curie in Paris, France, in June 2014. Throughout its history the conference has aimed to present the latest innovations and achievements in Decision Support Systems. This year the conference looks to the next generation with the theme of new technologies to enable DSS2.0. The topics covered include theoretical, empirical and design science research; case-based approaches in decision support systems; decision models in the real-world; healthcare information technology; decision making theory; knowledge management; knowledge and resource discovery; business intelligence; group decision support systems; collaborative decision making; analytics and ‘big data’; rich language for decision support; multimedia tools for DSS; Web 2.0 systems in decision support; context-based technologies for decision making; intelligent systems and technologies in decision support; organizational decision support; research methods in DSS 2.0; mobile DSS; competing on analytics; and social media analytics.
The book will be of interest to all those who develop or use Decision Support Systems. The variety of methods and applications illustrated by this international group of carefully reviewed papers should provide ideas and directions for future researchers and practitioners alike.
Advances in technology over the last several years have resulted in new and advanced methods to support decision-making. Decision Support Systems (DSS) are at the fore-front of information systems that incorporate various technologies and enable interaction with one or more users to help make complex decisions. For example, artificial intelligence has enabled people to make better decisions through the use of intelligent DSS. Other emerging areas in DSS research show that decision makers can operate in a more timely manner using real-time data, more accurately due to data mining and ‘big data’ methods, more strategically by considering a greater number of factors, more precisely and inclusively due to the availability of social networking data, and with a wider media reach with video and audio technology.
Since 1982, the IFIP TC8/Working Group 8.3 conferences have aimed to present the latest innovations and achievements of academic communities in Decision Support Systems. These advances include theory, systems, computer aided methods, algorithms, techniques, applications and technologies supporting decision making. A unique characteristic of WG8.3 conferences is a theme to reflect the academic interests and major trends in decision support systems at the time. In 2002 in Cork, Ireland, participants envisioned the future of the Internet. In Prato, Italy, in 2004, the “spirit of the humanist scholars of the Renaissance” was chosen as inspiration for decision making in uncertain times. Creativity and innovation were the focus in 2006 in London, UK, and in 2008 in Toulouse, France, participants looked to collaborative decision making support. The challenge of the socio-technical gap was the focus in 2010 in Lisbon, Portugal, and participants investigated fusing decision support into the fabric of people's lives in 2012 in Anávissos, Greece. This year, 2014, the conference looks to the next generation with a theme of new technologies to enable DSS 2.0. Also, this year, the conference itself tried a new approach by holding its meeting in conjunction with the Special Interest Group on Decision Support and Analytics (SIGDSA, formerly known as SIGDSS) organized since 2001 under the auspices of the Association for Information Systems (AIS). SIGDSA is a forum “to facilitate the exchange, development, communication, and dissemination of information about Decision Support, Analytics, Collaboration and Knowledge Management research and teaching issues in business, management, and organizational contexts among AIS members and in the larger community of IS/IT practitioners and scholars.” The common interests of these two groups served as fertile ground for new ideas and collaboration.
This volume of proceedings includes research topics in theoretical, empirical, design science research, and case-based approaches in: decision support systems, decision models in the real-world, healthcare information technology, decision making theory, knowledge management, knowledge and resource discovery, business intelligence, group decision support systems, collaborative decision making, analytics and ‘big data’, rich language for decision support, multimedia tools for DSS, Web 2.0 systems in decision support, context-based technologies for decision making, intelligent systems and technologies in decision support, organizational decision support, research methods in DSS 2.0, mobile DSS, competing on analytics, and social media analytics.
As editors, we express our gratitude to the authors for presenting their leading-edge research, the steering committees for their expert guidance, and the program committee and reviewers for their exceptional service in reviewing and ensuring the quality of papers in this volume. In particular, we would like to thank our hosts at the Université Pierre et Marie Curie of Paris, France, for the outstanding local arrangements for our international conference.
Sellinger School of Business and Management, Loyola University Maryland, USA
Lund University School of Economics and Management, Sweden
Faculdade de Ciências, Universidade de Lisboa, Portugal
Master Innovation Management, Université Pierre et Marie Curie, Paris, France
Evaluating patient's health status can be viewed as a multi attribute decision making (MADM) problem. Patients' problems are evaluated on the basis of symptoms. Contemporary information technology enables application of theoretical methods in practice. Such case is Henderson's model of basic leaving activities for patient health evaluation in nursing. In the paper we present the implementation of this model using DEX methodology. DEX is a qualitative MADM tool and offers user friendly acquisition and explanation of expert knowledge. The solution was tested in clinical practice and evaluated by using SWOT (strengths, weaknesses, opportunities and threats) analysis.
The emerging trend in treatment decision making for complex medical conditions is shifting to a collaborative model, where patients actively participate as decision makers. To facilitate this, online medical information must be fitting to the purpose of making sound treatment decisions. Underpinned by Herbert Simon's Nobel-winning work Administrative Behavior, we examine the treatment decision process in the context of Internet health information provision. Based on Simon's propositions, we propose a set of decision support features for evaluating Internet health information websites. We then use them to evaluate official Australian and international websites for Autism Spectrum Disorders (ASD), where the need for treatment decision support is prominent due to the diverse nature of the condition. The evaluation results indicate a general inadequacy in terms of Relevance under the Value proposition among the websites. Genuine individualized information based on patient's profile of symptoms, delivered by intelligent personalization technologies, should be further deployed to address this inadequacy. The theoretical contributions of this paper are: i) bridging online information quality model and classical decision making theory, and ii) analyzing online information provision based on Simon's bounded rationality. Whilst, the practical contributions are: i) to provide a set of decision support features as guidelines for ASD websites that ii) are extendable to other health domains and different technologies.
The purpose of this research is to analyse the organisational becoming produced by the implementation of the digitalised system for the Request and Medical Reports of Radiologic Examinations inside the Academic Integrated Hospital of Verona (AOUI) and by the related effects on the actors who interact with it. This system represents a module that will merge into the project of the Electronic Case History, which is currently underdeveloped. The adopted methodology is the qualitative study based on semi-structured interviews. Twelve people have been interviewed among the hospital's representatives, including the directorate (one interview), health management (two interviews), chief of information systems (one interview), radiologists (four interviews), radiology and neurology technicians (two interviews), health physicists (one interview), head nurse of the medicine ward and some nurses. This study highlights positive and negative elements on the organisational level and on the level concerning all people involved in the becoming.
This study aims at the possibility of early detection of seasonal influenza causing a major public health concern each year worldwide. Furthermore, the viability of social media analytics for the early detection of disease outbreak is examined. To conduct an analysis, three sets of data are used and investigated; search query data and two influenza related data collected from the nine US census bureau divisions on a weekly basis during a period from week 1, 2012 to week 52, 2013 from Google and Centers for Disease Control and Prevention (CDC), respectively. Pearson's correlation coefficient is calculated among the data as a statistical measure of the strength of a relationship, and the significant Pearson's rho confirms the existence of a very strong positive correlation. This study argues that the relative frequency of search queries is highly correlated with the actual number of influenza activity in each division of the US, and that social media analytics may be utilized to make an early detection of influenza epidemics possible. The importance of a detailed analysis is also discussed to assess the statistical methods for the phenomenon because the data from Google is still in its early stage which may contain inaccuracies.
This paper proposes a new approach to support medical decision making based on the analysis of multidisciplinary clinical discussions, which are becoming routine in hospitals and other health structures. In a medical discussion, participants make important pieces of knowledge explicit, by presenting different opinions, providing evidences that support hypotheses, and possibly arguing about clinical guidelines. However, this knowledge is often lost after the meeting is closed, since only the final decisions are written in patient records. Therefore, a computer-based system is proposed to help physicians manage clinical discussions, analyze them by means of argumentation-based techniques, and arrive, in the long run, at a synthesis of new knowledge fragments useful for future decisions. A preliminary experimentation of the system is presented in the domain of cognitive degeneration diseases.
Mobile Clinical Decision Support Systems (CDSS) aim to assist medical practitioners with decision making and provide an easy access to information on the move using mobile devices such as a mobile phone. Despite many benefits of mobile CDSS, these systems need to undergo a comprehensive evaluation to determine the correctness of the actions that decision maker take and validate the system's knowledge and recommendation. In this paper, we discuss the impact of mobile CDSS on decision making process and outcomes, and describe the multi-criteria evaluation of a mobile field triage decision support system in terms of effectiveness, efficiency, satisfaction and use. In this research, data was collected from a group of qualified paramedics using both quantitative and qualitative methods. The results and findings shed new light on the role of mobile decision support systems in improving healthcare delivery and provided better understanding of the barriers to the adoption of these systems and the impact of different stakeholders' views in evaluating the success of the DSS.
Recently, crime prevention is one of the overall strategies to reduce crime around the world including Malaysia. This is in lines with one of the Malaysian government agendas as stated in National Key Result Area (NKRA) which is to reduce crime. Because of the decision making process for crime prevention is manually done by the police, so it is difficult to determine the level of crime based on crime volume. That requires a method of selection to help the police to determine which is the most appropriate decision based on the level of crime. Therefore, this research developed prototype of decision support system (DSS) by using Mamdani-type fuzzy inference system (FIS) to classify the crime level and to improve the process of decision making for crime prevention. But, it is well-known that selection of membership functions (MF) is the key problem in the design of a FIS. Therefore, this paper outlines the basic comparisons between the triangular MF and trapezoidal MF. The experimental results of the two MFs are compared. It also shows which one is a better choice of the two MFs used in FIS in order to improve the efficiency of decision making for crime prevention. The result of the study indicates that triangular MF gives better classification of crime level but trapezoidal MF gives result closer to triangular MF.
This work focuses on the formalization of medical practices in chronic inflammatory bowel disease diagnosis as a contextual graph to identify a consensual methodology. Expert knowledge is more than domain knowledge because expert knowledge emerges from a contextualization process and expertise appears as “chunks of contextual knowledge”. The knowledge acquisition phase and the modeling of the expertise were organized around three workshops about the choice of diseases to study, the observation of how pathologists worked, the identification of similarity of pathologists' approaches and the proposal of a unified view. The “knowledge manager” was a physician knowing the expert knowledge used by experts but without their experience. A glocal search was identified in the decision-making process with a global exploration for detecting zones of interest, and a zoom inside zones of interest. This search concerns contextual elements at different levels of granularity as identified from the analysis of digital slides. The rest of the decision-making process includes the application of a set of criteria that are managed by a voting system that offers flexibility to address the variety of expert approaches. We discuss the role of the glocal approach in other domains like Control & Command rooms for the army and subway-line monitoring.
A decision support model aimed at the assessment of reputational risks associated with bank operation is presented in this paper. The innovative aspect of the model is that it combines different types and sources of information: structured and unstructured, quantitative and qualitative, internal and external. Unstructured, qualitative and external aspects are represented by sentiment of news and blogs about bank counterpart organisations. The model is multi-attribute and hierarchical, and is composed of three modules: basic data processing, qualitative evaluation, aggregation; these are described in detail. This paper also presents a prototype implementation of the model, illustrates its application on real-life data, and reports on experts' opinion about the model and its use.
Regression trees are helpful tools for knowledge discovery and decision support, due to their simple structure and the easiness to obtain them from data. Nonetheless, when applied to non-trivial datasets, they tend to grow according to the complexity of the data, becoming uneasy to interpret. In this work, we propose a clustering perturbation method to reduce the size of the regression tree obtained from each cluster. A prototype has been developed and tested on several regression datasets.
In the insurance sector, the assignment of business transactions to operational roles in the business process is a complex task that usually requires human intervention due to the lack of efficient and powerful automated decision making tools. A number of mechanisms and methods have been proposed to improve workloads' allocation in core business process in the insurance industry. This paper describes a novel solution, the iDispatcher, to efficiently assign and balance business transactions to line operators, in particular in the processes of underwriting and issuing policies. It is based on the use of a business rule engine that evaluates the intrinsic properties of a particular transaction and the specific abilities and technical skills of all available operators to find the best match. The iDispatcher benefits key business results by generating a more efficient operation based on the correct assignment of business transactions using a flexible and dynamic solution. The insurance companies will be able to make the right decision in the right moment for every incoming business request, and this represents a strategic difference in the market.
The focus in current decision management systems is on supporting selected decisions and transactional processes, rather than including decisions and information resulting from decisions and action processes over time. Thus, specific information is tailored to use specific DSS technology. The purpose of this research was to understand how decision information is organized in a complex, decision-rich organization. Documentation and archival records are the basis of this case study. An object-oriented framework with five key elements for linking decisions and information is introduced: issue, based-on, decision, agents, and consequence. It is suggested that an overall object-oriented approach would contribute to clarifying the decision context, the relationship to other decisions, and defining the roles and responsibilities of the decision and action team. Thus, the framework as a platfonn facilitates using different DSS technologies.
This short paper aims to outline the possibilities of fully utilizing Web 2.0 technologies and methodologies to build IT tools supporting the information and decision process within crisis management. Being a sort of snapshot report, it depicts a portion of research and development efforts on the integrated decision support platform for crisis management which the author has been working on as part of a research team and whose original concept was presented at the last IFIP WG 8.3 conference in Greece.
In this paper, we discuss a case study regarding transfer stations siting in a Solid Waste Management System, building a multi-criteria model potentially adequate to the involvement of multiple actors. A Decision Support System (DSS), named SABILOC (), integrating an Interactive Bi-objective Integer Programming Module and a Multi-attribute Module is used. The last module allows an a posteriori more detailed analysis of the solutions selected during the first module. Furthermore, the DSS includes meaningful graphical tools and integrates a Geographic Information System (GIS).
Recently, most organisations feel the need to modify existing business models and create new ones to adjust themselves to a dynamically changing business environment. However, a review of the business models literature reveals a lack of an effective business model construction tool and prioritisation framework. This despite the fact that the need for such a framework is clear, with recent studies revealing that most organisations are modifying existing business models and creating new ones. This paper utilises extant theory to construct a process-based tool whose objective is to enable organisations to construct effective business models. Furthermore, it applies Multi-Attribute Utility Theory to construct a Business Model Prioritisation framework, a rigorous decision making tool in enabling managers to prioritise the developed business models for implementation. Therefore, this paper not only contributes to theory but also has significant practical implications for organisations.
This paper presents a design science evaluation of a vital sign chart for an Aggregate-Weighted Track-and-Trigger System (AWTTS) developed by the Irish Health Service Executive (HSE). This system is known as the National Early Warning Score (NEWS), with the chart incorporated within NEWS known as the Early Warning Score (EWS) Chart. Presentations of patient vital sign data on charts provides an opportunity for healthcare professionals (HCPs) to process vital sign data and identify trends of patient deterioration. Due to the reality of working in a complex work environment processing this data can be difficult for HCPs. This research evaluates how useful experienced nurses perceive the EWS chart to be in the context of supporting them in processing vital sign data presented on the NEWS chart. This paper represents a reflective data-gathering phase for the development of a design framework for improving how vital sign data is visualised on electronic AWTTS charts. This paper also utilises the approach for Reflective Design Knowledge Synthesis (RDKS) to synthesise design knowledge inherent to the NEWS chart. The empirical findings of this study involving interviews of 8 nurses with an average of 21 years' experience demonstrate that the NEWS chart is significantly more useful than legacy vital sign charts that would have been previously used. Furthermore, the evaluation establishes which design features are perceived to be most useful for nurses when processing vital signs displayed on the NEWS chart.
The realities of the past that are embedded in the repository and shared by later groups constitute the collective memory. This paper outlines the specification of a collective decision-making system that utilizes the work of prior groups stored in the collective memory. We describe an approach that uses group memory based reasoning. In an effort to enhance utility, our group memory system is tested in a bank loan analysis domain, a semi-structured decision-making environment involving multiple attributes. The main goals are to reduce the time required to come to a decision, particularly, in a critical situation, to compensate for lack of experience of young bank consultant, and to distribute available experience to different sites.
Tendering management is a large and fragmented process implemented in various industries such as construction, logistics, pharmaceutical, and commerce. Tendering process is vital for a governing body that intends to acquire any goods or services from third parties for ensuring fair and transparent competition. Current electronic tender management does not have the necessary capabilities to automatically extract unstructured information on the tender document and hence, requires the decision maker to examine the information contained on the document one by one. In addition, the isolated tendering process leads to the ineffective communication between different stakeholders such as owners/clients, consultants, and contractors/suppliers to share and reuse information especially during decision-making. The increasing inconsistent and semantic heterogeneity information for the decision-making process requires the need to represent knowledge in a uniform format that is understandable to both humans and computers. Thus, the ontology-based decision support system architecture for tendering management is proposed to support information extraction and decision-making process. A prototype of ontology-based decision support system is developed using the case study of the construction tender evaluation process.
The adoption of social analytics heralds the arrival of a new paradigm in political campaign practice, driven by both behavioural science and social networks. Yet these domains have historically been in tension with opposite perspectives on political behaviour. The increasing focus on online social networks offers an opportunity to synthesise complementary research traditions on political behaviour to better understand the relationship between individual personality and information behaviour. We propose a model based on core dispositional personality traits, political participation as information consumption and information diffusion theory to explain online information behaviour during election events. Information diffusion requires users to perform several actions in combination - engage, rate content, comment, share and interpret information received. The research model enables us to observe in experimental settings how personality type guides interaction with and diffusion of political information across online social networks. The learned behaviours and direct responses of participants may help political campaigns in the design of future behavioural targeting strategies that activate social network effects to achieve campaign goals.
This preliminary research investigates the relationship between properties of social networks and coordination of sharing and access to expertise during disasters, which is extremely important in emergency response during disaster incidents. Therefore, knowing where specialized knowledge (expertise) is located, where it is needed and how it may be brought to bear in timely manner is extremely crucial. We also examine a theoretical model for the inherent role of social network structure, ties and position of actors for gaining access to and sharing of expertise. In this study, we explore specific questions such as –by: How centralization and efficiency in an individual's social network associate with coordination?, and Would network constraint and tie strength in an individual's social network negatively/positively associate with coordination?. The paper provides a theoretical account of how the social network-coordination model is developed and how the model has been preliminary validated by disaster management experts (CIO and managers) from State Emergency Services (SES), NSW, Australia. Results from semi-structured interviews with key managers from SES shows the significance of informal social network roles in their profession, especially for solving disaster management issues. Interviewees elaborate on the point of how social network directly enable their coordination at work. A research framework is also outlined in the conclusion section with directions for future social network analysis and research pathway.