for Journals by Title or ISSN
for Articles by Keywords
  Subjects -> BUSINESS AND ECONOMICS (Total: 3248 journals)
    - ACCOUNTING (101 journals)
    - BANKING AND FINANCE (274 journals)
    - BUSINESS AND ECONOMICS (1190 journals)
    - COOPERATIVES (4 journals)
    - ECONOMIC SCIENCES: GENERAL (183 journals)
    - HUMAN RESOURCES (95 journals)
    - INSURANCE (27 journals)
    - INTERNATIONAL COMMERCE (131 journals)
    - INVESTMENTS (27 journals)
    - MACROECONOMICS (16 journals)
    - MANAGEMENT (541 journals)
    - MARKETING AND PURCHASING (93 journals)
    - MICROECONOMICS (24 journals)
    - PUBLIC FINANCE, TAXATION (36 journals)

BUSINESS AND ECONOMICS (1190 journals)                  1 2 3 4 5 6 | Last

Showing 1 - 200 of 1566 Journals sorted alphabetically
4OR: A Quarterly Journal of Operations Research     Hybrid Journal   (Followers: 10)
Abacus     Hybrid Journal   (Followers: 13)
Accounting Forum     Hybrid Journal   (Followers: 25)
Acta Amazonica     Open Access   (Followers: 5)
Acta Commercii     Open Access   (Followers: 4)
Acta Oeconomica     Full-text available via subscription   (Followers: 2)
Acta Scientiarum. Human and Social Sciences     Open Access   (Followers: 7)
Acta Universitatis Danubius. Œconomica     Open Access   (Followers: 3)
Acta Universitatis Nicolai Copernici Zarządzanie     Open Access   (Followers: 4)
AD-minister     Open Access   (Followers: 3)
Admisi dan Bisnis     Open Access  
ADR Bulletin     Open Access   (Followers: 5)
Advances in Developing Human Resources     Hybrid Journal   (Followers: 23)
Advances in Economics and Business     Open Access   (Followers: 13)
AfricaGrowth Agenda     Full-text available via subscription   (Followers: 1)
African Affairs     Hybrid Journal   (Followers: 65)
African Development Review     Hybrid Journal   (Followers: 36)
African Journal of Business and Economic Research     Full-text available via subscription   (Followers: 3)
African Journal of Business Ethics     Open Access   (Followers: 6)
African Review of Economics and Finance     Open Access   (Followers: 3)
Afro-Asian Journal of Finance and Accounting     Hybrid Journal   (Followers: 7)
Afyon Kocatepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi     Open Access   (Followers: 3)
Agronomy     Open Access   (Followers: 10)
Akademika : Journal of Southeast Asia Social Sciences and Humanities     Open Access   (Followers: 6)
Alphanumeric Journal : The Journal of Operations Research, Statistics, Econometrics and Management Information Systems     Open Access   (Followers: 5)
American Economic Journal : Applied Economics     Full-text available via subscription   (Followers: 173)
American Enterprise Institute     Free  
American Journal of Business     Hybrid Journal   (Followers: 17)
American Journal of Business and Management     Open Access   (Followers: 53)
American Journal of Business Education     Open Access   (Followers: 12)
American Journal of Economics and Business Administration     Open Access   (Followers: 26)
American Journal of Economics and Sociology     Hybrid Journal   (Followers: 30)
American Journal of Evaluation     Hybrid Journal   (Followers: 14)
American Journal of Finance and Accounting     Hybrid Journal   (Followers: 21)
American Journal of Health Economics     Full-text available via subscription   (Followers: 13)
American Journal of Industrial and Business Management     Open Access   (Followers: 23)
American Journal of Medical Quality     Hybrid Journal   (Followers: 7)
American Law and Economics Review     Hybrid Journal   (Followers: 27)
ANALES de la Universidad Central del Ecuador     Open Access   (Followers: 2)
Annales de l'Institut Henri Poincare (C) Non Linear Analysis     Full-text available via subscription   (Followers: 1)
Annals in Social Responsibility     Full-text available via subscription  
Annals of Finance     Hybrid Journal   (Followers: 29)
Annals of Operations Research     Hybrid Journal   (Followers: 10)
Annual Review of Economics     Full-text available via subscription   (Followers: 32)
Anuario Facultad de Ciencias Económicas y Empresariales     Open Access   (Followers: 2)
Applied Developmental Science     Hybrid Journal   (Followers: 3)
Applied Economics     Hybrid Journal   (Followers: 42)
Applied Economics Letters     Hybrid Journal   (Followers: 29)
Applied Economics Quarterly     Full-text available via subscription   (Followers: 9)
Applied Financial Economics     Hybrid Journal   (Followers: 24)
Applied Mathematical Finance     Hybrid Journal   (Followers: 8)
Applied Stochastic Models in Business and Industry     Hybrid Journal   (Followers: 6)
Arab Economic and Business Journal     Open Access   (Followers: 4)
Archives of Business Research     Open Access   (Followers: 6)
Arena Journal     Full-text available via subscription   (Followers: 1)
Argomenti. Rivista di economia, cultura e ricerca sociale     Open Access   (Followers: 3)
ASEAN Economic Bulletin     Full-text available via subscription   (Followers: 5)
Asia Pacific Business Review     Hybrid Journal   (Followers: 7)
Asia Pacific Journal of Human Resources     Hybrid Journal   (Followers: 323)
Asia Pacific Viewpoint     Hybrid Journal   (Followers: 1)
Asia-Pacific Journal of Business Administration     Hybrid Journal   (Followers: 5)
Asia-Pacific Journal of Operational Research     Hybrid Journal   (Followers: 3)
Asia-Pacific Management and Business Application     Open Access   (Followers: 1)
Asian Business Review     Open Access   (Followers: 3)
Asian Case Research Journal     Hybrid Journal   (Followers: 1)
Asian Development Review     Open Access   (Followers: 13)
Asian Economic Journal     Hybrid Journal   (Followers: 8)
Asian Economic Papers     Hybrid Journal   (Followers: 7)
Asian Economic Policy Review     Hybrid Journal   (Followers: 4)
Asian Journal of Accounting and Governance     Open Access   (Followers: 3)
Asian Journal of Business Ethics     Hybrid Journal   (Followers: 9)
Asian Journal of Social Sciences and Management Studies     Open Access   (Followers: 6)
Asian Journal of Sustainability and Social Responsibility     Open Access   (Followers: 1)
Asian Journal of Technology Innovation     Hybrid Journal   (Followers: 8)
Asian-pacific Economic Literature     Hybrid Journal   (Followers: 5)
AStA Wirtschafts- und Sozialstatistisches Archiv     Hybrid Journal   (Followers: 5)
ATA Journal of Legal Tax Research     Full-text available via subscription   (Followers: 4)
Atlantic Economic Journal     Hybrid Journal   (Followers: 11)
Australasian Journal of Regional Studies, The     Full-text available via subscription   (Followers: 1)
Australian Cottongrower, The     Full-text available via subscription   (Followers: 1)
Australian Economic Papers     Hybrid Journal   (Followers: 31)
Australian Economic Review     Hybrid Journal   (Followers: 4)
Australian Journal of Maritime and Ocean Affairs     Hybrid Journal   (Followers: 9)
Balkan Region Conference on Engineering and Business Education     Open Access   (Followers: 1)
Baltic Journal of Real Estate Economics and Construction Management     Open Access   (Followers: 2)
Banks in Insurance Report     Hybrid Journal   (Followers: 1)
BBR - Brazilian Business Review     Open Access   (Followers: 4)
Benchmarking : An International Journal     Hybrid Journal   (Followers: 10)
Benefit : Jurnal Manajemen dan Bisnis     Open Access   (Followers: 1)
BER : Consumer Confidence Survey     Full-text available via subscription   (Followers: 3)
BER : Economic Prospects : An Executive Summary     Full-text available via subscription  
BER : Economic Prospects : Full Survey     Full-text available via subscription   (Followers: 1)
BER : Intermediate Goods Industries Survey     Full-text available via subscription  
BER : Manufacturing Survey : Full Survey     Full-text available via subscription   (Followers: 1)
BER : Motor Trade Survey     Full-text available via subscription  
BER : Retail Sector Survey     Full-text available via subscription   (Followers: 1)
BER : Retail Survey : Full Survey     Full-text available via subscription   (Followers: 1)
BER : Survey of Business Conditions in Building and Construction : An Executive Summary     Full-text available via subscription   (Followers: 3)
BER : Survey of Business Conditions in Manufacturing : An Executive Summary     Full-text available via subscription   (Followers: 2)
BER : Survey of Business Conditions in Retail : An Executive Summary     Full-text available via subscription   (Followers: 3)
BER : Trends : Full Survey     Full-text available via subscription   (Followers: 1)
BER : Wholesale Sector Survey     Full-text available via subscription  
Berkeley Business Law Journal     Free   (Followers: 9)
Bio-based and Applied Economics     Open Access   (Followers: 1)
Biodegradation     Hybrid Journal   (Followers: 1)
Biology Direct     Open Access   (Followers: 7)
BizInfo (Blace) Journal of Economics, Management and Informatics     Open Access  
Black Enterprise     Full-text available via subscription  
Board & Administrator for Administrators only     Hybrid Journal  
Boletim Técnico do Senac     Open Access  
Border Crossing : Transnational Working Papers     Open Access   (Followers: 3)
Briefings in Real Estate Finance     Hybrid Journal   (Followers: 5)
British Journal of Industrial Relations     Hybrid Journal   (Followers: 36)
Brookings Papers on Economic Activity     Open Access   (Followers: 46)
Brookings Trade Forum     Full-text available via subscription   (Followers: 3)
BRQ Business Research Quarterly     Open Access   (Followers: 2)
Building Sustainable Legacies : The New Frontier Of Societal Value Co-Creation     Full-text available via subscription   (Followers: 1)
Bulletin of Economic Research     Hybrid Journal   (Followers: 17)
Bulletin of Geography. Socio-economic Series     Open Access   (Followers: 5)
Bulletin of Indonesian Economic Studies     Hybrid Journal   (Followers: 3)
Bulletin of the Dnipropetrovsk University. Series : Management of Innovations     Open Access   (Followers: 1)
Business & Entrepreneurship Journal     Open Access   (Followers: 19)
Business & Information Systems Engineering     Hybrid Journal   (Followers: 4)
Business & Society     Hybrid Journal   (Followers: 10)
Business : Theory and Practice / Verslas : Teorija ir Praktika     Open Access   (Followers: 1)
Business and Economic Research     Open Access   (Followers: 6)
Business and Management Horizons     Open Access   (Followers: 12)
Business and Management Research     Open Access   (Followers: 18)
Business and Management Studies     Open Access   (Followers: 11)
Business and Politics     Hybrid Journal   (Followers: 8)
Business and Professional Communication Quarterly     Hybrid Journal   (Followers: 7)
Business and Society Review     Hybrid Journal   (Followers: 5)
Business Economics     Hybrid Journal   (Followers: 9)
Business Ethics Quarterly     Full-text available via subscription   (Followers: 12)
Business Ethics: A European Review     Hybrid Journal   (Followers: 18)
Business Horizons     Hybrid Journal   (Followers: 7)
Business Information Review     Hybrid Journal   (Followers: 14)
Business Management and Strategy     Open Access   (Followers: 41)
Business Research     Hybrid Journal   (Followers: 2)
Business Strategy and the Environment     Hybrid Journal   (Followers: 13)
Business Strategy Review     Hybrid Journal   (Followers: 7)
Business Strategy Series     Hybrid Journal   (Followers: 6)
Business Systems & Economics     Open Access   (Followers: 2)
Business Systems Research Journal     Open Access   (Followers: 5)
Business, Management and Education     Open Access   (Followers: 17)
Business, Peace and Sustainable Development     Full-text available via subscription   (Followers: 3)
Bustan     Hybrid Journal  
Cadernos EBAPE.BR     Open Access   (Followers: 1)
Cambridge Journal of Economics     Hybrid Journal   (Followers: 61)
Cambridge Journal of Regions, Economy and Society     Hybrid Journal   (Followers: 9)
Canadian Journal of Administrative Sciences / Revue Canadienne des Sciences de l Administration     Hybrid Journal   (Followers: 1)
Canadian Journal of Economics/Revue Canadienne d`Economique     Hybrid Journal   (Followers: 29)
Canadian journal of nonprofit and social economy research     Open Access   (Followers: 2)
Capitalism and Society     Hybrid Journal   (Followers: 2)
Capitalism Nature Socialism     Hybrid Journal   (Followers: 17)
Case Studies in Business and Management     Open Access   (Followers: 10)
CBU International Conference Proceedings     Open Access   (Followers: 2)
Central European Business Review     Open Access   (Followers: 1)
Central European Journal of Operations Research     Hybrid Journal   (Followers: 5)
Central European Journal of Public Policy     Open Access   (Followers: 2)
CESifo Economic Studies     Hybrid Journal   (Followers: 17)
Chain Reaction     Full-text available via subscription  
Challenge     Full-text available via subscription   (Followers: 4)
China & World Economy     Hybrid Journal   (Followers: 15)
China : An International Journal     Full-text available via subscription   (Followers: 19)
China Economic Journal: The Official Journal of the China Center for Economic Research (CCER) at Peking University     Hybrid Journal   (Followers: 13)
China Economic Review     Hybrid Journal   (Followers: 10)
China Finance Review International     Hybrid Journal   (Followers: 5)
China Nonprofit Review     Hybrid Journal   (Followers: 3)
China perspectives     Open Access   (Followers: 12)
Chinese Economy     Full-text available via subscription  
Ciência & Saúde Coletiva     Open Access   (Followers: 2)
CLIO América     Open Access   (Followers: 1)
Cliometrica     Hybrid Journal   (Followers: 4)
COEPTUM     Open Access  
Community Development Journal     Hybrid Journal   (Followers: 27)
Compensation & Benefits Review     Hybrid Journal   (Followers: 7)
Competition & Change     Hybrid Journal   (Followers: 11)
Competitive Intelligence Review     Hybrid Journal   (Followers: 2)
Competitiveness Review : An International Business Journal incorporating Journal of Global Competitiveness     Hybrid Journal   (Followers: 5)
Computational Economics     Hybrid Journal   (Followers: 9)
Computational Mathematics and Modeling     Hybrid Journal   (Followers: 8)
Computer Law & Security Review     Hybrid Journal   (Followers: 17)
Computers & Operations Research     Hybrid Journal   (Followers: 12)
Construction Innovation: Information, Process, Management     Hybrid Journal   (Followers: 14)
Contemporary Wales     Full-text available via subscription   (Followers: 1)
Contextus - Revista Contemporânea de Economia e Gestão     Open Access   (Followers: 1)
Contributions to Political Economy     Hybrid Journal   (Followers: 5)
Corporate Communications An International Journal     Hybrid Journal   (Followers: 7)
Corporate Philanthropy Report     Hybrid Journal   (Followers: 2)
Corporate Reputation Review     Hybrid Journal   (Followers: 5)
Creative and Knowledge Society     Open Access   (Followers: 8)
Creative Industries Journal     Hybrid Journal   (Followers: 8)
CRIS - Bulletin of the Centre for Research and Interdisciplinary Study     Open Access   (Followers: 1)
Crossing the Border : International Journal of Interdisciplinary Studies     Open Access   (Followers: 4)
Cuadernos de Administración (Universidad del Valle)     Open Access   (Followers: 2)
Cuadernos de Economía     Open Access   (Followers: 2)
Cuadernos de Economia - Latin American Journal of Economics     Open Access   (Followers: 2)
Cuadernos de Estudios Empresariales     Open Access   (Followers: 2)
Current Opinion in Creativity, Innovation and Entrepreneurship     Open Access   (Followers: 12)

        1 2 3 4 5 6 | Last

Journal Cover Decision Support Systems
  [SJR: 2.262]   [H-I: 95]   [16 followers]  Follow
   Hybrid Journal Hybrid journal (It can contain Open Access articles)
   ISSN (Print) 0167-9236
   Published by Elsevier Homepage  [3177 journals]
  • Omnichannel business research: Opportunities and challenges
    • Authors: Yang Chen; Christy M.K. Cheung; Chee-Wee Tan
      Pages: 1 - 4
      Abstract: Publication date: Available online 29 March 2018
      Source:Decision Support Systems
      Author(s): Yang Chen, Christy M.K. Cheung, Chee-Wee Tan
      Detailing the opportunities and challenges of omnichannel business, this paper serves as an editorial note to the corresponding special issue. We advance a framework that delineates extant literature on omnichannel business into four predominant research streams according to their perspective (i.e., consumer versus retailer) and research orientation (i.e., diagnostic versus prescriptive). For each of the four research streams, we articulate its current state of research and describe how select articles assembled in this special issue enhance the stream.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.007
      Issue No: Vol. 109 (2018)
  • Mindfully going omni-channel: An economic decision model for evaluating
           omni-channel strategies
    • Authors: Sabiölla Hosseini; Marieluise Merz; Maximilian Röglinger; Annette Wenninger
      Pages: 74 - 88
      Abstract: Publication date: Available online 31 January 2018
      Source:Decision Support Systems
      Author(s): Sabiölla Hosseini, Marieluise Merz, Maximilian Röglinger, Annette Wenninger
      In the digital age, customers want to define on their own how to interact with organizations during their customer journeys. Thus, many organizations struggle to implement an omni-channel strategy (OCS) that meets their customers' channel preferences and can be operated efficiently. Despite this high practical need, research on omni-channel management predominantly takes a descriptive perspective. What is missing is prescriptive knowledge that guides organizations in the valuation and selection of an appropriate OCS. Most existing studies investigate single facets of omni-channel management in detail while neglecting the big picture. They also require customer journeys to follow sequential and organization-defined purchase decision processes. To address this research gap, we propose an economic decision model that considers online and offline channels, the opening and closing of channels, non-sequential customer journeys, and customers' channel preferences. Drawing from the principles of value-based management, the decision model recommends choosing the OCS with the highest contribution to an organization's long-term firm value. We applied and validated the decision model based on real-world data from a German bank.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.01.010
      Issue No: Vol. 109 (2018)
  • Cyber-analytics: Modeling factors associated with healthcare data breaches
    • Authors: Alexander McLeod; Diane Dolezel
      Pages: 57 - 68
      Abstract: Publication date: Available online 2 March 2018
      Source:Decision Support Systems
      Author(s): Alexander McLeod, Diane Dolezel
      The purpose of this study was to develop a model of factors associated with healthcare data breaches. Variables were operationalized as the healthcare facilities' level of exposure, level of security, and organizational factors. The outcome variable was the binary value for data breach/no data breach. Because healthcare data breaches carry the risk of personal health information exposure, corruption or destruction, this study is important to the healthcare field. Data were obtained from the Department of Health and Human Services database of healthcare facilities reporting data breaches and from a large national database of technical and organizational infrastructure information. Binary logistic regression was utilized to examine a representative data breach model. Results indicate several exposure, security and organizational factors significantly associated with healthcare data breaches.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.02.007
      Issue No: Vol. 108 (2018)
  • Exploring the influence of flow and psychological ownership on security
           education, training and awareness effectiveness and security compliance
    • Authors: Chul Woo Yoo; G. Lawrence Sanders; Robert P. Cerveny
      Pages: 107 - 118
      Abstract: Publication date: Available online 2 March 2018
      Source:Decision Support Systems
      Author(s): Chul Woo Yoo, G. Lawrence Sanders, Robert P. Cerveny
      The purpose of this study is to investigate the impact of flow and psychological ownership on security education, training, and awareness (SETA) effectiveness, self-efficacy, and security compliance intention. The important role of experiencing flow in SETA is presented as focal antecedents of psychological ownership, self-efficacy, SETA effectiveness, and security compliance intention. To achieve these goals, we propose a theoretical framework and analyze survey data to test the hypotheses. Flow components in SETA are extended to include challenge, feedback, autonomy, immersion, and social interaction. The results illustrate that experiencing flow in SETA shows significant relationships with SETA effectiveness and psychological ownership, which in turn positively influence security compliance intention. Appropriate theoretical contributions and managerial implications are also discussed.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.02.009
      Issue No: Vol. 108 (2018)
  • Platform adoption by mobile application developers: A multimethodological
    • Authors: Jaeki Song; Jeff Baker; Ying Wang; Hyoung Yong Choi; Anol Bhattacherjee
      Pages: 26 - 39
      Abstract: Publication date: Available online 5 January 2018
      Source:Decision Support Systems
      Author(s): Jaeki Song, Jeff Baker, Ying Wang, Hyoung Yong Choi, Anol Bhattacherjee
      This paper investigates the factors that influence the adoption of IT platforms by software developers and how those factors differ from those that influence IT adoption by end-users. We take a multi-methodological approach, beginning with an interpretive field study where we interview mobile application developers. In the initial interpretive phase, we identify a comprehensive set of influences on developers' platform adoption, comparing them with the factors that have been identified in previous studies of end-user adoption, noting key differences. In the second phase, we empirically test the factors identified in our interviews. We find several key differences between end-user adoption of IT and developer adoption of IT platforms. Most notably, we observe the importance of network externality considerations when developers make an adoption decision, a consideration that is largely absent for end-users. Our study is among the first to comment on B2B and B2C issues in the adoption phenomenon where developers adopt a platform as technology producers (a B2B consideration) in order to ultimately provide mobile applications to end-users who are technology consumers (a B2C consideration).

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2017.12.013
      Issue No: Vol. 107 (2018)
  • Can irrelevant benchmark information help when making business decisions
           under uncertainty' An empirical investigation of the newsvendor game
    • Authors: Tong Wu; Abraham Seidmann
      Pages: 40 - 51
      Abstract: Publication date: Available online 2 January 2018
      Source:Decision Support Systems
      Author(s): Tong Wu, Abraham Seidmann
      Firms often compensate employees based on their relative performance in the most recent business period. These firms need to consider what type of performance information to share with their employees in order to obtain better outcomes in the long run, without diminishing staff motivation. In this paper, we empirically investigate the impact of sharing irrelevant benchmark “information” (e.g., information about the interim winner's performance) when individuals are making repeated decisions under uncertainty. The decision-making context used is the newsvendor problem, which is a canonical framework for operations management decision making. The newsvendor problem occurs in many business contexts, such as buying fashion goods for retail, setting safety stock levels, setting target inventory levels for perishable goods, selecting the right capacity for a service facility, and overbooking customers. Theoretically, information about the interim winner's performance has no value for making improved decisions in future rounds, and it might even be misleading. Surprisingly, we find that displaying such irrelevant benchmark information results in significantly improved decisions overall, as compared to a control group; this additional display may motivate participants to perform better. We also identify two personality traits related to impulsivity which moderate this positive information display effect.

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2017.12.014
      Issue No: Vol. 107 (2018)
  • Disentangling consumer recommendations: Explaining and predicting airline
           recommendations based on online reviews
    • Authors: Michael Siering; Amit V. Deokar; Christian Janze
      Pages: 52 - 63
      Abstract: Publication date: Available online 11 January 2018
      Source:Decision Support Systems
      Author(s): Michael Siering, Amit V. Deokar, Christian Janze
      Consumer recommendations of products and services are important performance indicators for organizations to gain feedback on their offerings. Furthermore, they are important for prospective customers to learn from prior consumer experiences. In this study, we focus on user-generated content, in particular online reviews, to investigate which service aspects are evaluated by consumers and how these factors explain a consumer's recommendation. Further, we investigate how recommendations can be predicted automatically based on such user-driven responses. We disentangle the recommendation decision by performing explanatory and predictive analyses focusing on a sample of airline reviews. We identify core and augmented service aspects expressed in the online review. We then show that service aspect-specific sentiment indicators drive the decision to recommend an airline and that these factors can be incorporated in a predictive model using data mining techniques. We also find that the business model of an airline being reviewed, whether low cost or full service, is also an applicable consideration. Our results are highly relevant for practitioners to analyze and act on consumer feedback in a prompt manner, along with the ability of gaining a deeper understanding of the service from multiple aspects. Also, potential travelers can benefit from this approach by getting an aggregated view on service quality.

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2018.01.002
      Issue No: Vol. 107 (2018)
  • Failure pattern-based ensembles applied to bankruptcy forecasting
    • Authors: Philippe du Jardin
      Pages: 64 - 77
      Abstract: Publication date: March 2018
      Source:Decision Support Systems, Volume 107
      Author(s): Philippe du Jardin
      Bankruptcy prediction models that rely on ensemble techniques have been studied in depth over the last 20 years. Within most studies that have been performed on this topic, it appears that any ensemble-based model often achieves better results than those estimated with a single model designed using the base classifier of the ensemble, but it is not uncommon that the results of the former model do not outperform those of a single model when estimated with any other classifier. Indeed, an ensemble of decision trees is almost always more accurate than a single tree but not necessarily more than a neural network or a support vector machine. We know that the accuracy of an ensemble used to forecast firm bankruptcy is closely related to its ability to capture the variety of bankruptcy situations. But the fact that it may not be more efficient than a single model suggests that current techniques used to handle such a variety are not completely satisfactory. This is why we have looked for a method that makes it possible to better embody this diversity than current ones do. The technique proposed in this article relies on the quantification, using Kohonen maps, of temporal patterns that characterized the financial health of a set of companies, and on the use of an ensemble of incremental size maps to make forecasts. The results show that such models lead to better predictions than those that can be achieved with traditional methods.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.01.003
      Issue No: Vol. 107 (2018)
  • Automatic feature weighting for improving financial Decision Support
    • Authors: Yosimar Oswaldo Serrano-Silva; Yenny Villuendas-Rey; Cornelio Yáñez-Márquez
      Pages: 78 - 87
      Abstract: Publication date: Available online 31 January 2018
      Source:Decision Support Systems
      Author(s): Yosimar Oswaldo Serrano-Silva, Yenny Villuendas-Rey, Cornelio Yáñez-Márquez
      We propose a novel methodology for improving financial Decision Support Systems (DSS) through automatic feature weighting. Using this methodology, we show that automatic feature weighting leads to a significant improvement in the performance of decision-making algorithms over financial data, which are the key of financial DSS. The statistical analysis carried out shows that metaheuristic algorithms are good for automatic feature weighting, and that Differential Evolution (DE) offers a good trade-off between decision-making performance and computational cost. We believe these results contribute to the development of novel financial DSS.
      Graphical abstract image

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2018.01.005
      Issue No: Vol. 107 (2018)
  • Detection of Online Phishing Email using Dynamic Evolving Neural Network
           Based on Reinforcement Learning
    • Authors: Sami Smadi; Nauman Aslam; Li Zhang
      Pages: 88 - 102
      Abstract: Publication date: Available online 17 January 2018
      Source:Decision Support Systems
      Author(s): Sami Smadi, Nauman Aslam, Li Zhang
      Despite state-of-the-art solutions to detect phishing attacks, there is still a lack of accuracy for the detection systems in the online mode which leading to loopholes in web-based transactions. In this research, a novel framework is proposed which combines a neural network with reinforcement learning to detect phishing attacks in the online mode for the first time. The proposed model has the ability to adapt itself to produce a new phishing email detection system that reflects changes in newly explored behaviours, which is accomplished by adopting the idea of reinforcement learning to enhance the system dynamically over time. The proposed model solve the problem of limited dataset by automatically add more emails to the offline dataset in the online mode. A novel algorithm is proposed to explore any new phishing behaviours in the new dataset. Through rigorous testing using the well-known data sets, we demonstrate that the proposed technique can handle zero-day phishing attacks with high performance levels achieving high accuracy, TPR, and TNR at 98.63%, 99.07%, and 98.19% respectively. In addition, it shows low FPR and FNR, at 1.81% and 0.93% respectively. Comparison with other similar techniques on the same dataset shows that the proposed model outperforms the existing methods.
      Graphical abstract image

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2018.01.001
      Issue No: Vol. 107 (2018)
  • Time-aware cloud service recommendation using similarity-enhanced
           collaborative filtering and ARIMA model
    • Authors: Shuai Ding; Yeqing Li; Desheng Wu; Youtao Zhang; Shanlin Yang
      Pages: 103 - 115
      Abstract: Publication date: Available online 8 January 2018
      Source:Decision Support Systems
      Author(s): Shuai Ding, Yeqing Li, Desheng Wu, Youtao Zhang, Shanlin Yang
      The quality of service (QoS) of cloud services change frequently over time. Existing service recommendation approaches either ignore this property or address it inadequately, leading to ineffective service recommendation. In this paper, we propose a time-aware service recommendation (taSR) approach to address this issue. We first develop a novel similarity-enhanced collaborative filtering (CF) approach to capture the time feature of user similarity and address the data sparsity in the existing PITs (point in time). We then apply autoregressive integrated moving average model (ARIMA) to predict the QoS values in the future PIT under QoS instantaneity. We evaluate the proposed approach and compare it to the state-of-the-art. Our experimental results show that taSR achieves significant performance improvements over existing approaches.

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2017.12.012
      Issue No: Vol. 107 (2018)
  • Unsupervised tip-mining from customer reviews
    • Authors: Di Zhu; Theodoros Lappas; Juheng Zhang
      Pages: 116 - 124
      Abstract: Publication date: Available online 6 February 2018
      Source:Decision Support Systems
      Author(s): Di Zhu, Theodoros Lappas, Juheng Zhang
      In recent years, large review-hosting platforms have extended their functionality to allow their users to submit tips: short pieces of text that deliver valuable insight on a specific aspect of the reviewed business. These tips are meant to serve as a concise source of information that complements the often overwhelming number of customer reviews. Recent work has tackled the problem of automatically generating tips by mining review text. The motivation for this effort is to obtain tips for businesses or business aspects that have been overlooked by users. Another motivating factor is the quality of the user-submitted tips, which often provide trivial or redundant information. Existing tip-mining methods are limited by a reliance on training data, which is unlikely to be available and is also very costly to create for different domains. In this work, we present TipSelector, a completely unsupervised algorithm that delivers high quality-tips without the need for annotated training data. We verify the efficacy of TipSelector via an evaluation that includes real data from the hospitality industry and comparisons with the state-of-the-art. A secondary contribution of our work is a method for automatically evaluating tip-mining algorithms without humans in the loop. As we demonstrate in our experiments, this method can be used to enable large-scale evaluations and complement the user studies that are typically used for this purpose.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.01.011
      Issue No: Vol. 107 (2018)
  • Assessing data quality – A probability-based metric for semantic
    • Authors: Bernd Heinrich; Mathias Klier; Alexander Schiller; Gerit Wagner
      Abstract: Publication date: Available online 6 April 2018
      Source:Decision Support Systems
      Author(s): Bernd Heinrich, Mathias Klier, Alexander Schiller, Gerit Wagner
      We present a probability-based metric for semantic consistency using a set of uncertain rules. As opposed to existing metrics for semantic consistency, our metric allows to consider rules that are expected to be fulfilled with specific probabilities. The resulting metric values represent the probability that the assessed dataset is free of internal contradictions with regard to the uncertain rules and thus have a clear interpretation. The theoretical basis for determining the metric values are statistical tests and the concept of the p-value, allowing the interpretation of the metric value as a probability. We demonstrate the practical applicability and effectiveness of the metric in a real-world setting by analyzing a customer dataset of an insurance company. Here, the metric was applied to identify semantic consistency problems in the data and to support decision-making, for instance, when offering individual products to customers.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.011
  • Factors influencing hospital readmission penalties: Are they really under
           hospitals' control'
    • Authors: Rupinder P. Jindal; Dinesh K. Gauri; Gaganjot Singh; Sean Nicholson
      Abstract: Publication date: Available online 3 April 2018
      Source:Decision Support Systems
      Author(s): Rupinder P. Jindal, Dinesh K. Gauri, Gaganjot Singh, Sean Nicholson
      The Hospital Readmissions Reduction Program (HRRP) established by the Centers for Medicare & Medicaid Services (CMS) penalizes hospitals that have excessive readmission rates. Research is needed to determine if there are factors that influence readmission penalties but may be out of the control of hospitals. In this study, we compare a set of geo-demographic, hospital, and quality of care characteristics of hospitals penalized by HRRP with those not penalized, and determine these characteristics' association with the likelihood of penalization as well as the extent of penalties. We collected and integrated data from multiple sources such as the HRRP Supplemental Data File, the Hospital Compare database, CMS Impact files, the HCAHPS survey, and the U.S. census. We followed a two-step estimation procedure. First, we estimated a logistic regression model to find the relationship between various characteristics and whether a hospital was penalized. Second, we estimated a linear regression model to find the relationship between these characteristics and the extent of penalties. Results show that both the likelihood and the extent of penalties varied across several characteristics related to geo-demographics (such as location in the census division, urban vs. rural location, and racial make-up of the area), hospitals (such as ownership, bed capacity, teaching status, and case mix index), and quality of care (such as quality of communication by doctors and information provided at the time of discharge). Although quality of care characteristics are under hospitals' control and can be improved, geo-demographic and hospital characteristics are likely consistent over time and largely out of the control of hospitals. The study supports the case for a comprehensive revision of HRRP's scoring methodology to calculate readmission penalties.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.006
  • Toward a real-time and budget-aware task package allocation in spatial
    • Authors: Pengkun Wu; Eric W.T. Ngai; Yuanyuan Wu
      Abstract: Publication date: Available online 30 March 2018
      Source:Decision Support Systems
      Author(s): Pengkun Wu, Eric W.T. Ngai, Yuanyuan Wu
      With the development of mobile technology, spatial crowdsourcing has become a popular approach in collecting data or road information. However, as the number of spatial crowdsourcing tasks becomes increasingly large, the accurate and rapid allocation of tasks to suitable workers has become a major challenge in managing spatial outsourcing. Existing studies have explored the task allocation algorithms with the aim of guaranteeing quality information from workers. However, studies focusing on the task allocation rate when allocating tasks are still lacking despite the increasing unallocated rates of spatial crowdsourcing tasks in the real world. Although the task package is a commonly known scheme used to allocate tasks, it has not been applied to allocate spatial crowdsourcing tasks. To fill these gaps in the literature, we propose a real-time, budget-aware task package allocation for spatial crowdsourcing (RB-TPSC) with the dual objectives of improving the task allocation rate and maximizing the expected quality of results from workers under limited budgets. The proposed RB-TPSC enables spatial crowdsourcing task requester to automatically make key task allocation decisions on the following: (1) to whom should the task be allocated, (2) how much should the reward be for the task, and (3) whether and how the task is packaged with other tasks.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.010
  • A visual analytics system to support tax evasion discovery
    • Authors: Walter Didimo; Luca Giamminonni; Giuseppe Liotta; Fabrizio Montecchiani; Daniele Pagliuca
      Abstract: Publication date: Available online 29 March 2018
      Source:Decision Support Systems
      Author(s): Walter Didimo, Luca Giamminonni, Giuseppe Liotta, Fabrizio Montecchiani, Daniele Pagliuca
      This paper describes TaxNet, a decision support system for tax evasion discovery, based on a powerful visual language and on advanced network visualization techniques. It has been developed in cooperation with the Italian Revenue Agency, where it is currently used. TaxNet allows users to visually define classes of suspicious patterns, it exploits effective graph pattern matching technologies to rapidly extract subgraphs that correspond to one or more patterns, it provides facilities to conveniently merge the results, and it implements new ad-hoc centrality indexes to rank taxpayers based on their fiscal risk. Moreover, it offers a visual interface to analyze and interact with those networks that match a desired pattern. The paper discusses the results of an experimental study and some use cases conducted with expert officers on real data and in a real working environment. The experiments give evidence of the effectiveness of our system.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.008
  • Improving website structure through reducing information overload
    • Authors: Min Chen
      Abstract: Publication date: Available online 29 March 2018
      Source:Decision Support Systems
      Author(s): Min Chen
      It is well known that website success relies heavily on its usability. Previous studies find that website usability depends greatly upon its visual complexity which has significant effects on users' psychological perception and cognitive load. In this study, we use a page's outdegree as one measurement for its visual complexity. In general, outdegrees should be kept not too high in page design as large outdegrees are often signs of high page complexity which can adversely affect user navigation. This is particularly desirable and critical for maintaining website structures, because as a website evolves over time, the need for information also changes. Website structures must be updated periodically to align with users' information needs. In this process, obsolete links should be removed to avoid clustering of links that could cause information overload to users. However, the need to slim down website structures is understudied in the literature. In this paper, we propose a mathematical programming model that reduces information load by removing links from highly clustered pages while minimizing the impact to users. Results from tests on a real dataset indicate that the model not only significantly reduces page complexity with little impact on user navigation, but also can be solved effectively. The model is also tested on large synthetic datasets to demonstrate its remarkable scalability.

      PubDate: 2018-04-15T23:04:27Z
  • The expected value of perfect information in unrepeatable decision-making
    • Authors: Mercedes Boncompte
      Abstract: Publication date: Available online 20 March 2018
      Source:Decision Support Systems
      Author(s): Mercedes Boncompte
      This paper reflects on the concept of the “expected value of perfect information” (EVPI) and the procedure used to determine it. It is widely accepted that this value is the difference between the expected value when we have perfect information and the best expected value provided by alternatives. However, this difference often results in values that no rational decision-maker would accept. Here, we overcome this difficulty by defining the “value of perfect information for the problem” (VPIP) where we consider not only the price of perfect information (EVPI) but also two additional parameters: the “loss to be avoided” and “the most favourable payoff in the worst scenario”. In this way, we are able to obtain a more accurate value of the amount a decision-maker might be willing to pay for perfect information. We also seek to show that the indiscriminate employment of probability theory, based by definition on the repetition of the experiment, can be misleading in the case of decisions which, owing to the very nature of the problem, are unrepeatable.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.003
  • An empirical examination of the influence of biased personalized product
           recommendations on consumers' decision making outcomes
    • Authors: Bo Xiao; Izak Benbasat
      Abstract: Publication date: Available online 16 March 2018
      Source:Decision Support Systems
      Author(s): Bo Xiao, Izak Benbasat
      To assist consumers in product search and selection while shopping online, many e-commerce retailers have implemented web-based product recommendation agents (PRAs). However, consumers are empowered to the extent that the PRAs provide true personalization by recommending products based solely on, and thus best representing, consumers' preferences. This study constructs and empirically tests a theoretical model that examines how biased recommendations from PRAs influence consumers' decision quality and decision effort. The results of an online experiment show that consumers are extremely vulnerable to biased personalized recommendations from online PRAs. In addition, our results extend prior research by identifying perceived personalization as a critical mechanism driving the influence of biased PRA on consumers' decision quality and decision effort. This study fills a void in the literature and calls attention to an insidious form of manipulation made possible by innovative technologies supporting e-commerce.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.005
  • Business social media analytics: Characterization and conceptual framework
    • Authors: Clyde W. Holsapple; Shih-Hui Hsiao; Ram Pakath
      Abstract: Publication date: Available online 13 March 2018
      Source:Decision Support Systems
      Author(s): Clyde W. Holsapple, Shih-Hui Hsiao, Ram Pakath
      A substantial portion of internet usage today involves social media applications. Aside from personal use, given the vast amount of content stored, and rapid diffusion of information, in social media, businesses have begun exploiting social media for competitive advantage. Its popularity has led to the recognition of Social Media Analytics (SMA) as a distinct, albeit formative, sub-field within the Analytics field. Against this backdrop, we examine available characterizations of SMA that collectively identify various considerations of interest. However, their diversity suggests the need for adopting a concise, unifying SMA definition. We present a definition that subsumes salient aspects of existing characterizations and incorporates novel features of interest to Business SMA. Further, we examine available conceptual frameworks for Business SMA and advance a framework that comprehensively models the Business SMA phenomenon. We also conduct a survey of recently published SMA research in the premier, academic Management Information Systems journals and use some of the surveyed papers to validate our framework.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.004
  • The truck driver scheduling problem with fatigue monitoring
    • Authors: Zachary E. Bowden; Cliff T. Ragsdale
      Abstract: Publication date: Available online 11 March 2018
      Source:Decision Support Systems
      Author(s): Zachary E. Bowden, Cliff T. Ragsdale
      In the United States, approximately 4000 fatalities due to truck and bus crashes occur each year. Of these, up to 20% are estimated to involve fatigued drivers [48]. However, no model currently exists that incorporates a measure of drowsiness or fatigue into the Truck Driver Scheduling Problem (TDSP). We introduce a fatigue-aware model for determining the optimal schedule for a driver while maintaining an acceptable level of alertness as well as abiding by time windows and hours of service (HOS) regulations. Additionally, we examine a shortcoming in existing regulations, specifically related to assumptions made about the rest and alertness of a driver at the start of the workweek.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.002
  • Use of online information and suitability of target in shoplifting: A
           routine activity based analysis
    • Authors: Jaeung Lee; Melchor C. de Guzman; Nasim Talebi; Swaroop Kumar Korni; Donald Szumigala; H. Raghav Rao
      Abstract: Publication date: Available online 2 March 2018
      Source:Decision Support Systems
      Author(s): Jaeung Lee, Melchor C. de Guzman, Nasim Talebi, Swaroop Kumar Korni, Donald Szumigala, H. Raghav Rao
      Shoplifting is the largest contributor to inventory depletion in the US retail sector. To effectively mitigate and prevent such criminal activity, one needs to understand the shoplifter's perspectives on the suitability of the retail products targeted for shoplifting. Extending Routine Activity Theory (RAT) from criminology literature to include usefulness of online information, we analyze shoplifters' perceptions regarding future target suitability by considering a retail item's value, inertia, visibility, and accessibility (VIVA). We also examine how online information about a target's disposal and guardianship can influence shoplifters' decisions. In this paper, the Partial Least Squares (PLS) method was used to analyze data collected in the Western New York area over a one-year period. The results show positive effects of value and reverse inertia on target suitability. Interestingly, the relationship between target suitability and the usefulness of online information about post-shoplifting disposal activity was negative. Implications for future research and practical applications for shoplifting prevention are discussed.

      PubDate: 2018-04-15T23:04:27Z
      DOI: 10.1016/j.dss.2018.03.001
  • Secondhand seller reputation in online markets: A text analytics framework
    • Authors: Runyu Chen; Yitong Zheng; Wei Xu; Minghao Liu; Jiayue Wang
      Abstract: Publication date: Available online 24 February 2018
      Source:Decision Support Systems
      Author(s): Runyu Chen, Yitong Zheng, Wei Xu, Minghao Liu, Jiayue Wang
      With the rapid development of e-commerce, a new type of secondhand e-commerce website has appeared in recent years. Any user can have his or her own shop and list superfluous items for sale online without much supervision. These secondhand e-commerce platforms maximize the economic value of secondhand markets online, but buyers risk conducting unpleasant transactions with low-reputation sellers. The main contribution of our research is the design of a text analytics framework to assess secondhand sellers' reputation. In addition, we develop a new aspect-extraction method that combines the results of domain ontology and topic modeling to extract topical features from product descriptions. We conduct our experiments based on a real-word dataset crawled from XianYu. The experimental results reveal that our ontology-based topic model method outperforms a traditional topic model method. Furthermore, the proposed framework performs well in different item categories. The managerial implication of our research is that potential buyers can prejudge the reputation of secondhand sellers when making purchase decisions. The results can support a more effective development of online secondhand markets.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.02.008
  • ExUP recommendations: Inferring user's product metadata preferences from
           single-criterion rating systems
    • Authors: Alfred Castillo; Debra Vander Meer; Arturo Castellanos
      Abstract: Publication date: Available online 24 February 2018
      Source:Decision Support Systems
      Author(s): Alfred Castillo, Debra Vander Meer, Arturo Castellanos
      Recommendation systems make use of complex algorithms and methods to provide recommendations to consumers. Typically, online rating schemes use a single rating metric that captures the overall user experience with a product. Nevertheless, this might hinder the intricacies of how a product's attributes influence an individual's preferences. While it is possible to use sentiment and semantic analysis to interpret free text in user reviews, if available, to gain insight into a user's reasons for a product rating, these methods are expensive to implement and error prone, and rely on significant data input from the user. To overcome these challenges, we propose a method for inferring user preferences and generating recommendations without relying on the availability or quality of text reviews. Specifically, our method is designed to use existing product metadata and user rating patterns to shed light on how the attributes of a product correspond to individual preferences. Our method uses only the user's history of ratings and the corresponding product attributes to generate predicted ratings for products a user has not yet experienced. This work extends existing work in this area by focusing on multi-valued attributes, and considering the distinct impact of each attribute value in a user's preferences. In terms of computational complexity, our method runs in linear time, making it feasible for real-time implementations. Our experimental results showed that, compared with the two best-performing existing state of the art methods, our method provided review score predictions with up to: 47.7% greater precision, 6.9% greater recall, and 20.5% greater F-measure than existing methods.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.02.006
  • Explaining and predicting online review helpfulness: The role of content
           and reviewer-related signals
    • Authors: Michael Siering; Jan Muntermann; Balaji Rajagopalan
      Abstract: Publication date: Available online 19 February 2018
      Source:Decision Support Systems
      Author(s): Michael Siering, Jan Muntermann, Balaji Rajagopalan
      Online reviews provide information about products and services valuable for consumers in the context of purchase decision making. Online reviews also provide additional value to online retailers, as they attract consumers. Therefore, identifying the most-helpful reviews is an important task for online retailers. This research addresses the problem of predicting the helpfulness of online product reviews by developing a comprehensive research model guided by the theoretical foundations of signaling theory. Thereby, our research model posits that the reviewer of a product sends signals to potential buyers. Using a sample of product reviews, we test our model and observe that review content-related signals (i.e., specific review content and writing styles) and reviewer-related signals (i.e., reviewer expertise and non-anonymity) both influence review helpfulness. Furthermore, we find that the signaling environment affects the signal impact and that incentives provided to reviewers influence the signals sent. To demonstrate the practical relevance of our results, we illustrate by means of a problem-specific evaluation scenario that our model provides superior predictions of review helpfulness compared to earlier approaches. Furthermore, we provide evidence that the proposed evaluation scenario provides deeper insights than classical performance metrics. Our findings are highly relevant for online retailers seeking to reduce information overload and consumers' search costs as well as for reviewers contributing online product reviews.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.01.004
  • A decision support system for integrated container handling in a
           transshipment hub
    • Authors: Pasquale Legato; Rina Mary Mazza
      Abstract: Publication date: Available online 12 February 2018
      Source:Decision Support Systems
      Author(s): Pasquale Legato, Rina Mary Mazza
      The productivity of a maritime container terminal can be improved through a model-driven decision support system (DSS) focused on a better integration among container handling operations occurring across the quay, transfer and yard areas. Integration is pursued to minimize the blocking, locking and other queuing phenomena which are unavoidable, especially when human-operated equipment is shared in a real environment subjected to several random events and activities. An integrated queuing network is proposed in this paper as the natural modeling paradigm for a DSS aimed to highlight and quantify the blocking, locking and other queuing phenomena experienced in real practice. After an in-depth discussion of the limitations of solving the queuing network model analytically, discrete-event simulation is adopted as solution method. Numerical examples referred to a case study for a real transshipment hub return reliable estimates for the above queuing phenomena. They illustrate how the queuing-based DSS may effectively support the operations manager in determining the proper operational policies and equipment management with respect to a proficient integration of container handling operations.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.02.004
  • The blocking effect of preconceived bias
    • Authors: Andy Luse; Anthony M. Townsend; Brian E. Mennecke
      Abstract: Publication date: Available online 10 February 2018
      Source:Decision Support Systems
      Author(s): Andy Luse, Anthony M. Townsend, Brian E. Mennecke
      Research has shown that preexisting individual biases about a product can have negative effects on future purchase behavior or use. While extensively studied in marketing, the role of informational blocking with regard to decision making about information technologies has not been investigated. This research explores the interplay of biases as a form of information blocking and explores these biased-blocking effects in the context of technology. Results show that while different types of experience have a significant effect on the decision to use a technology product, this effect is completely blocked by the preconceived bias of the individual about the technology.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.02.002
  • Predicting tax avoidance by means of social network analytics
    • Authors: Jasmien Lismont; Eddy Cardinaels; Liesbeth Bruynseels; Sander De Groote; Bart Baesens; Wilfried Lemahieu; Jan Vanthienen
      Abstract: Publication date: Available online 9 February 2018
      Source:Decision Support Systems
      Author(s): Jasmien Lismont, Eddy Cardinaels, Liesbeth Bruynseels, Sander De Groote, Bart Baesens, Wilfried Lemahieu, Jan Vanthienen
      This study predicts tax avoidance by means of social network analytics. We extend previous literature by being the first to build a predictive model including a larger variation of network features. We construct a network of firms connected through shared board membership. Then, we apply three analytical techniques, logistic regression, decision trees, and random forests; to create five models using either firm characteristics, network characteristics or different combinations of both. A random forest including firm characteristics, network characteristics of firms and network characteristics of board members provides the best performance with a minimal increase of 7 pp in AUC. Hence, including network effects significantly improves the predictive ability of tax avoidance models, implying that board members exhibit specific knowledge which can carry over across firms. We find that having board members with no connections to low-tax companies lowers the likelihood of being a low-tax firm. Similarly, the higher the average tax rate of the companies a board member is connected to, the lower the chance of being low-tax. On the other hand, being connected to more low-tax firms increases the probability of being low-tax. Consistent with prior literature on firm-specific variables, PP&E has a positive influence on the probability of being low-tax, while EBITDA has a negative effect. Our results are informative for companies as to the director expertise they want to attract in their boards. Additionally, financial analysts and regulatory agencies can use our insights to predict which firms are likely to be low-tax and potentially at risk.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.02.001
  • Digital strategies for two-sided markets: A case study of shopping malls
    • Authors: Johan Frishammar; Javier Cenamor; Harald Cavalli-Björkman; Emma Hernell; Johan Carlsson
      Abstract: Publication date: Available online 9 February 2018
      Source:Decision Support Systems
      Author(s): Johan Frishammar, Javier Cenamor, Harald Cavalli-Björkman, Emma Hernell, Johan Carlsson
      Digitalization is fundamentally changing the retailing ecosystem for shopping malls as digital and analogue elements get increasingly intertwined. We conceptualize shopping malls as two-sided markets whose primary function is connecting shoppers and retailers. By means of an interpretative case study, the article then presents an omnichannel strategy typology for how shopping malls can meet the evolving digitalization challenge. We identify three generic strategies labeled digital awaiter, digital data gatherer, and digital embracer. The paper provides implications for research in omnichannel strategies, digitalization, and two-sided markets by explicating different strategies that involve physical and digital resources, and different ecosystem agents, i.e., retailers and shoppers. It also provides insights for other organizations beyond retailing and which operate under a two-sided market regime.

      PubDate: 2018-02-26T10:42:08Z
      DOI: 10.1016/j.dss.2018.02.003
  • Cannibalization and competition effects on a manufacturer's retail channel
           strategies: Implications on an omni-channel business model
    • Authors: Jae-Cheol Kim; Se-Hak Chun
      Abstract: Publication date: Available online 31 January 2018
      Source:Decision Support Systems
      Author(s): Jae-Cheol Kim, Se-Hak Chun
      This paper analyzes two effects caused by “channel conflict”, which occurs when firms newly add a direct online channel via the Internet or a mobile device. The first is an “intra-cannibalization effect” between the firms' existing retail channel and the new online channel, and the second is the “inter-competition effect” between manufacturers and retailers in the supply chain. In particular, this paper investigates a manufacturer's retailing channel strategy considering the relative market power between a manufacturer and a retailer in the supply chain, which has been rarely considered in previous studies. This paper shows the manufacturer's channel strategies: (i) if customers are very heterogeneous with regard to their receptiveness to online shopping, the manufacturer may use a multi-channel strategy. (ii) if the customer sector becomes homogeneous, the manufacturer will become more willing to adopt an omni-channel strategy. (iii) if customers are neither similar nor very different, the manufacturer uses a brick-and-mortar strategy. This paper also shows results on the issue of channel conflict in terms of market power: (i) the retailer may voluntarily limit its market power and thus, self-created competition in the retail market alleviates the problem of double-markup to some extent. (ii) the manufacturer can use an online channel when inter-competition effect becomes severe.

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2018.01.007
  • Channel integration quality, perceived fluency and omnichannel service
           usage: The moderating roles of internal and external usage experience
    • Authors: Xiao-Liang Shen; Yang-Jun Li; Yongqiang Sun; Nan Wang
      Abstract: Publication date: Available online 31 January 2018
      Source:Decision Support Systems
      Author(s): Xiao-Liang Shen, Yang-Jun Li, Yongqiang Sun, Nan Wang
      Along with the rapid development of in-store technology, multichannel service is being shifted to omnichannel. By integrating different parallel channels, omnichannel service delivers customers an integrated, seamless and consistent cross-channel shopping experience. To better understand this emerging phenomenon, this study intends to explore the potential drivers of omnichannel service usage. Drawing upon Wixom & Todd framework, this study develops a research model by including object-based beliefs (i.e., channel integration quality) and behavioral beliefs (i.e., perceived fluency). In addition, behavior-based traits (i.e., internal and external usage experience) are hypothesized as moderating the effects of behavioral beliefs on usage behavior. Using an online survey of 401 omnichannel users, the findings demonstrate that channel integration quality significantly affects perceived fluency across different channels, which in turn explains 55% of the variance in omnichannel service usage. The results also show that internal usage experience weakens, whereas external usage experience enhances the effect of perceived fluency on omnichannel service usage. Limitations and implications of this study are further discussed.

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2018.01.006
  • Omnichannel businesses in the publishing and retailing industries:
           Synergies and tensions between coexisting online and offline business
    • Authors: Martin Wiener; Nadja Hoßbach; Carol Saunders
      Abstract: Publication date: Available online 31 January 2018
      Source:Decision Support Systems
      Author(s): Martin Wiener, Nadja Hoßbach, Carol Saunders
      Since the emergence of the Internet, many brick-and-mortar companies from various industries have established an online business model (BM) alongside their traditional offline BM. Despite the increasing coexistence of online and offline BMs within a single company, however, most prior research has focused on studying online and offline BMs in isolation. Consequently, still little is known about the interplay of dual BMs in omnichannel businesses. We address this research gap through an empirical investigation of the synergies and tensions that arise from coexisting online and offline BMs as well as the factors that influence the emergence of such synergies and tensions. Drawing on a series of six case studies with three publishers and three retailers, we identify an extended set of BM synergies and tensions, which concern all major BM dimensions. In addition, our case analysis reveals that companies are able to exploit different synergies, but also face different tensions between their online and offline BMs. The observed differences can be traced back to the level of online-offline BM integration, online-offline product distinctions (e.g., in terms of product content and publication cycles), and general organization context factors (e.g., offline brand strength, organization structure). By uncovering both the benefits and the complexity of running online and offline BMs in parallel, our study contributes to the theoretical understanding of omnichannel businesses, and provides managers with practical guidance on how to design, integrate, and manage their dual BMs successfully.

      PubDate: 2018-02-05T13:41:08Z
      DOI: 10.1016/j.dss.2018.01.008
  • Augmenting processes with decision intelligence: Principles for integrated
    • Authors: Faruk Johannes; Smedt Jan Vanthienen
      Abstract: Publication date: Available online 28 December 2017
      Source:Decision Support Systems
      Author(s): Faruk Hasić, Johannes De Smedt, Jan Vanthienen
      Until recently decisions were mostly modelled within the process. Such an approach was shown to impair the maintainability, scalability, and flexibility of both processes and decisions. Lately, literature is moving towards a separation of concerns between the process and decision model. Most notably, the introduction of the Decision Model and Notation (DMN) standard provides a suitable solution for filling the void of decision representation. This raises the question whether decisions and processes can easily be separated and consistently integrated. We introduce an integrated way of modelling the process, while providing a decision model which encompasses the process in its entirety, rather than focusing on local decision points only. Specifically, this paper contributes formal definitions for decision models and for the integration of processes and decisions. Additionally, inconsistencies between process and decision models are identified and we remedy those inconsistencies by establishing Five Principles for integrated Process and Decision Modelling (5PDM). The principles are subsequently illustrated and validated on a case of a Belgian accounting company.

      PubDate: 2018-02-05T13:41:08Z
  • Improving prognosis and reducing decision regret for pancreatic cancer
           treatment using artificial neural networks
    • Authors: Steven Walczak; Vic Velanovich
      Abstract: Publication date: Available online 16 December 2017
      Source:Decision Support Systems
      Author(s): Steven Walczak, Vic Velanovich
      Cancer is a worldwide health problem with extremely high morbidity and mortality. Pancreatic cancer specifically is the fourth leading cause of death by cancer in the United States and is a leading cause of cancer deaths worldwide. The optimal treatment for pancreatic cancer is resection surgery, but even with surgery many patients suffer high morbidity and mortality, leading to regret in physicians over whether or not the optimal course of treatment with regard to the patient's quality of life was made. Patients also suffer regret concerning the morbidity associated with treatment. An artificial neural network is developed to predict 7-month survival of pancreatic cancer patients that achieves over a 91% sensitivity and an overall accuracy above 70%. The artificial neural network outcome predictions may be used as an additional source of information to assist physicians and patients in selecting the treatment that provides the best quality of life for the patient and reduces treatment decision regret.

      PubDate: 2017-12-26T17:01:30Z
      DOI: 10.1016/s0016-5085(17)34157-4
      Issue No: Vol. 152, No. 5 (2017)
  • A synthetic informative minority over-sampling (SIMO) algorithm leveraging
           support vector machine to enhance learning from imbalanced datasets
    • Authors: Saeed Piri; Dursun Delen; Tieming Liu; Hamed M. Zolbanin
      Pages: 12 - 27
      Abstract: Publication date: Available online 29 November 2017
      Source:Decision Support Systems
      Author(s): Saeed Piri, Dursun Delen, Tieming Liu
      Developing decision support systems (DSS) based on imbalanced datasets is one the critical challenges in data mining and decision-analytics. A dataset is called imbalanced when the number of examples from one class outnumbers the number of the instances from another class. Learning from imbalanced datasets is one of the major challenges in machine learning. While a standard classifier could have a very good performance on a balanced dataset, when applied to an imbalanced dataset, its performance deteriorates dramatically. This poor performance is rather troublesome, especially in detecting the minority class, which usually is the class of interest. Therefore, the poor performance of machine learning techniques, which are used to develop DSS, negatively affect the practicality of DSS in real word problems. Over-sampling the minority class is one of the most promising remedies for imbalanced data learning. In this study, we propose a new synthetic informative minority over-sampling (SIMO) algorithm leveraging support vector machine (SVM). In this algorithm, first SVM is applied to the original imbalanced dataset, then, minority examples close to the SVM decision boundary, as the informative minority examples are over-sampled. We also developed another version of SIMO and call it weighted SIMO (W-SIMO). W-SIMO is different from SIMO in the degree of over-sampling the informative minority examples. In W-SIMO, incorrectly classified informative minority examples are over-sampled with a higher degree compared to the correctly classified informative minority examples. In this way, there is more focus on incorrectly classified minority examples. The over-sampled dataset can be used to train any classifier. We applied these algorithms to the 15 publicly available benchmark imbalanced datasets and assessed their performance in comparison with existing approaches in the area of imbalanced data learning. The results showed that our algorithms had the best performance in all datasets compared to other approaches.

      PubDate: 2017-12-13T01:14:36Z
      DOI: 10.1016/j.dss.2017.05.012
      Issue No: Vol. 101 (2017)
  • Will firm's marketing efforts on owned social media payoff' A
           quasi-experimental analysis of tourism products
    • Authors: Hsin-Lu Chang; Yen-Chun Chou Dai-Yu Sou-Chein
      Abstract: Publication date: Available online 24 December 2017
      Source:Decision Support Systems
      Author(s): Hsin-Lu Chang, Yen-Chun Chou, Dai-Yu Wu, Sou-Chein Wu
      A growing number of travel agencies in the tourism industry use social media to promote their services and reach target customers despite some doubt regarding the effectiveness of these tools. Nevertheless, most prior studies adopt a customer-centric perspective to explore the usefulness of earned social media (e.g., eWOM) and its influences on customer behavior. Few have examined a firm's owned social media strategy (e.g., a Facebook brand page) in online social interactions. This paper distinguishes owned media from earned media by site ownerships and communication paths. We study a firm's marketing efforts on its owned media (Facebook brand page) and evaluate the resulting effect on sales. Based on the cognitive fit theory, we further explore whether a firm can moderate such effects by promoting different types of products. Working with a leading travel agency in Taiwan, we collected a matched sample of products with Facebook marketing (treatment group) and those without Facebook marketing (control group). Using a quasi-experimental design and difference-in-difference (DID) estimation, we evaluate the effect of a firm's efforts on Facebook marketing campaigns after controlling time-fixed selection bias and common time-series heterogeneity. While the method is powerful and intuitive, its validity largely relies on the common trend assumption. A concise discussion on caveats of DID estimation is provided to carefully examine our findings, as well as serve as a simple guidance for IS research. The results show that Facebook campaign activities have a positive impact on purchases of tourism products. Furthermore, sales are more likely to increase when a travel agency promotes tourism products that are highly structured, medium-priced, or medium-length, or that require more tourist involvement. Such effects are further examined across different quantiles of sales and in different time spans to see when product moderations are more prominent. The empirical findings facilitate decision-making of e-commerce managers in the tourism industry not only by justifying the effectiveness as well as budget allocation of owned social media marketing, but also by providing a rudimentary guidance on the product selection in Facebook marketing campaigns.

      PubDate: 2017-12-26T17:01:30Z
  • Optimal Pricing in E-Commerce Based on Sparse and Noisy Data
    • Authors: Josef Bauer; Dietmar Jannach
      Abstract: Publication date: Available online 14 December 2017
      Source:Decision Support Systems
      Author(s): Josef Bauer, Dietmar Jannach
      In today’s transparent markets, e-commerce providers often have to adjust their prices within short time intervals, e.g., to take frequently changing prices of competitors into account. Automating this task of determining an “optimal” price (e.g., in terms of profit or revenue) with a learning-based approach can however be challenging. Often, only few data points are available, making it difficult to reliably detect the relationships between a given price and the resulting revenue or profit. In this paper, we propose a novel machine-learning based framework for estimating optimal prices under such constraints. The framework is generic in terms of the optimality criterion and can be customized in different ways. At its core, it implements a novel algorithm based on Bayesian inference combined with bootstrap-based confidence estimation and kernel regression. Simulation experiments show that our method is favorable over existing dynamic pricing strategies. Furthermore, the method led to a significant increase in profit and revenue in a real-world evaluation.

      PubDate: 2017-12-26T17:01:30Z
  • Visibility of corporate websites: The role of information prosociality
    • Authors: Gautam Pant; Shagun Pant
      Abstract: Publication date: Available online 14 December 2017
      Source:Decision Support Systems
      Author(s): Gautam Pant, Shagun Pant
      With an ever expanding content and user base, the Web presents information discovery and consumption challenges for both consumers and producers of information. Producers of information strive for visibility among consumers who have limited attention. Corporate websites are a primary digital marketing channel for firms through which they seek to gain a bigger share of their stakeholders' (i.e., customers, investors, communities) attention. Using observations spanning several years we study the website visibility, as measured by user traffic, of more than 2500 public firms and its association with properties of corporate websites and the corresponding firms. One property that is of particular interest to us is the availability of “community-engaging” pages, i.e., pages that support blogs or forums on the website or provide links to external social media platforms such as Facebook. These community-engaging pages signify online prosocial services provided by firms. We find that websites with larger number of community-engaging pages are associated with higher visibility. This provides a novel empirical support for the promotion and use of social media content and tools on websites of firms. We also find that websites with more specific content are associated with lower visibility while providing more out-links is associated with higher visibility. We observe these results consistently over time. These associations are observed while controlling for the size of the firms, types of their industries, the magnitude of media attention and other firm-level heterogeneity. Finally, machine learning models derived from our empirical analysis provide strong predictive utility for out-of-sample data.

      PubDate: 2017-12-26T17:01:30Z
  • Predicting graft survival among kidney transplant recipients: A Bayesian
           decision support model decision support systems
    • Authors: Kazim Topuz; Ferhat Zengul Ali Dag Ammar Almehmi Mehmet Bayram
      Abstract: Publication date: Available online 9 December 2017
      Source:Decision Support Systems
      Author(s): Kazim Topuz, Ferhat D. Zengul, Ali Dag, Ammar Almehmi, Mehmet Bayram Yildirim
      Predicting the graft survival for kidney transplantation is a high stakes undertaking considering the shortage of available organs and the utilization of healthcare resources. The strength of any predictive model depends on the selection of proper predictors. However, despite improvements in acute rejection management and short-term graft survival, the accurate prediction of kidney transplant outcomes remains suboptimal. Among other approaches, machine-learning techniques have the potential to offer solutions to this prediction problem in kidney transplantation. This study offers a novel methodological solution to this prediction problem by: (a) analyzing the retrospective database including >31,000 U.S. patients; (b) introducing a comprehensive feature selection framework that accounts for medical literature, data analytics methods and elastic net (EN) regression (c) using sensitivity analyses and information fusion to evaluate and combine features from several machine learning approaches (i.e., support vector machines (SVM), artificial neural networks (ANN), and Bootstrap Forest (BF)); (d) constructing several different scenarios by merging different sets of features that are optioned through these fused data mining models and statistical models in addition to expert knowledge; and (e) using best performing sets in Bayesian belief network (BBN) algorithm to identify non-linear relationships and the interactions between explanatory factors and risk levels for kidney graft survival. The results showed that the predictor set obtained through fused data mining model and literature review outperformed the all other alternative predictors sets with the scores of 0.602, 0.684, 0.495 for F-Measure, Average Accuracy, and G-Mean, respectively. Overall, our findings provide novel insights about risk prediction that could potentially help in improving the outcome of kidney transplants. This methodology can also be applied to other similar transplant data sets.

      PubDate: 2017-12-13T01:14:36Z
  • The effect of intrinsic and extrinsic quality cues of digital video games
           on sales: An empirical investigation
    • Authors: Hoon Choi; Myung Dawn Medlin Charlie Chen
      Abstract: Publication date: Available online 8 December 2017
      Source:Decision Support Systems
      Author(s): Hoon S. Choi, Myung S. Ko, Dawn Medlin, Charlie Chen
      This study examines the effect of product quality cues on sales of digital video games, using signaling theory as a theoretical model. The quality cues are examined from two angles: intrinsic and extrinsic. The intrinsic cues, in this study, include company reputation, newness, and retro features and extrinsic cues include review valence, product popularity, price, and user engagement. Based on a publicly available panel data of 142,590 observations for 5415 digital video games, our empirical results suggest that both intrinsic and extrinsic quality cues affect sales of digital video games. Company reputation of a digital video game, however, does not have a significant effect on sales. Although an overall relationship between price and sales is positive, this is not the case for less popular digital video games. This study provides the implications for IS research and practice.

      PubDate: 2017-12-13T01:14:36Z
  • Feature selection using firefly optimization for classification and
           regression models
    • Authors: Zhang Kamlesh; Mistry Chee Peng Lim Siew Chin Neoh
      Abstract: Publication date: Available online 7 December 2017
      Source:Decision Support Systems
      Author(s): Li Zhang, Kamlesh Mistry, Chee Peng Lim, Siew Chin Neoh
      In this research, we propose a variant of the Firefly Algorithm (FA) for discriminative feature selection in classification and regression models for supporting decision making processes using data-based learning methods. The FA variant employs Simulated Annealing (SA)-enhanced local and global promising solutions, chaotic-accelerated attractiveness parameters and diversion mechanisms of weak solutions to escape from the local optimum trap and mitigate the premature convergence problem in the original FA algorithm. A total of 29 classification and 11 regression benchmark data sets have been used to evaluate the efficiency of the proposed FA model. It shows statistically significant improvements over other state-of-the-art FA variants and classical search methods for diverse feature selection problems. In short, the proposed FA variant offers an effective method to identify optimal feature subsets in classification and regression models for supporting data-based decision making processes.

      PubDate: 2017-12-13T01:14:36Z
  • The privacy trade-off for mobile app downloads: The roles of app value,
           intrusiveness, and privacy concerns
    • Authors: Verena Wottrich; Eva van Reijmersdal Edith Smit
      Abstract: Publication date: Available online 6 December 2017
      Source:Decision Support Systems
      Author(s): Verena M. Wottrich, Eva A. van Reijmersdal, Edith G. Smit
      Today, mobile app users regularly “pay” for various mobile services, such as social networking or entertainment apps, by accepting app permission requests, thereby sharing personal data with apps. Privacy calculus theory has established that individuals disclose personal information based on a cost-benefit trade-off. In the mobile app context, however, this notion needs more support, because existing studies have only measured costs and benefits or forced a trade-off. Conducting two online experiments among Western European app users (N 1 =183; N 2 =687), this study replicates earlier findings and provides more-profound insights into the boundary conditions of the privacy calculus by showing that app value (i.e., benefits) trumps the costs (i.e., intrusiveness, privacy concerns) in the privacy trade-off.

      PubDate: 2017-12-13T01:14:36Z
  • Change detection model for sequential cause-and-effect relationships
    • Authors: Tony Cheng-Kui; Huang Pu-Tai Yang Jen-Hung Teng
      Abstract: Publication date: Available online 5 December 2017
      Source:Decision Support Systems
      Author(s): Tony Cheng-Kui Huang, Pu-Tai Yang, Jen-Hung Teng
      Detecting changes of behaviors or events is crucial when updating existing knowledge in a dynamic business environment. Currently, data analysts can immediately collect data and easily access existing knowledge. However, that knowledge can also rapidly become outdated. This study discusses a form of knowledge, classifiable sequential patterns (CSPs), defined as s → c, where s is a temporal sequence; c is a class label; and “→” is a sign which implies the sequential relationships between s (cause) and c (effect). If the CSP evolves into another, and the new knowledge is not updated, decision-makers would continue to work with the obsolete CSP. To the authors' knowledge, no study has addressed the topic of change mining in CSPs. To address this research gap, this study proposes a novel change-mining model, SeqClassChange, to identify changes in CSPs. Experiments were conducted with a real-world dataset to evaluate the proposed model.

      PubDate: 2017-12-13T01:14:36Z
  • Comparing fingerprint-based biometrics authentication versus traditional
           authentication methods for e-payment
    • Authors: Obi Ogbanufe; Dan Kim
      Abstract: Publication date: Available online 21 November 2017
      Source:Decision Support Systems
      Author(s): Obi Ogbanufe, Dan J. Kim
      Biometrics authentication for electronic payment is generally viewed as a quicker, convenient and a more secure means to identify and authenticate users for online payment. This view is mostly anecdotal and conceptual is nature. The aim of the paper is to shed light on the comparison of perceptions and beliefs of different authentication methods for electronic payment (i.e., credit card, credit card with PIN, and fingerprint biometrics authentication) in an e-commerce context. As theoretical foundation, the valence framework is used in understanding and explaining the individual's evaluation of benefit and risk concerning the payment methods. We propose a research model with hypotheses that evaluate and compare the individual's perceptions of the payment authentication methods, trust of the online store, and the willingness to continue using the website account associated with the payment authentication method. An experiment is used to test the hypotheses. The results show that biometrics authentication significantly influences the individual's security concern, perceived usefulness, and trust of online store. Theoretically, through the study's context – biometrics versus credit card authentication – evidence is provided for the importance of the individual's perceptions, concerns, and beliefs in the use of biometrics for electronic payments. Managerial implications include shedding light on the perceptions and concerns of secure authentication and the need for implementing biometrics authentication for electronic payments.

      PubDate: 2017-12-13T01:14:36Z
  • Using contextual features and multi-view ensemble learning in product
           defect identification from online discussion forums
    • Authors: Yao Liu; Cuiqing Jiang Huimin Zhao
      Abstract: Publication date: Available online 20 October 2017
      Source:Decision Support Systems
      Author(s): Yao Liu, Cuiqing Jiang, Huimin Zhao
      As social media are continually gaining more popularity, they have become an important source for manufacturers to collect information related to defects on their products from consumers. Researchers have started to develop automated models to identify mentions of product defects from social media, such as online discussion forums. In this paper, we propose a novel method for product defect identification from online forums, addressing two inadequacies in previous studies, namely, the inadequate use of information contained in replies and the straightforward use of standard single classifier methods. Our method incorporates contextual features derived from replies and uses a multi-view ensemble learning method specifically tailored to the problem on hand. A case study in the automotive industry demonstrates the utilities of both novelties in our method.

      PubDate: 2017-10-26T06:09:41Z
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-