for Journals by Title or ISSN
for Articles by Keywords
  Subjects -> BUSINESS AND ECONOMICS (Total: 3133 journals)
    - ACCOUNTING (92 journals)
    - BANKING AND FINANCE (267 journals)
    - BUSINESS AND ECONOMICS (1158 journals)
    - COOPERATIVES (4 journals)
    - ECONOMIC SCIENCES: GENERAL (169 journals)
    - HUMAN RESOURCES (94 journals)
    - INSURANCE (22 journals)
    - INTERNATIONAL COMMERCE (126 journals)
    - INVESTMENTS (27 journals)
    - MACROECONOMICS (15 journals)
    - MANAGEMENT (526 journals)
    - MARKETING AND PURCHASING (89 journals)
    - MICROECONOMICS (24 journals)
    - PUBLIC FINANCE, TAXATION (35 journals)

BUSINESS AND ECONOMICS (1158 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: 6)
Acta Universitatis Danubius. Œconomica     Open Access   (Followers: 3)
Acta Universitatis Nicolai Copernici Zarządzanie     Open Access   (Followers: 4)
AD-minister     Open Access   (Followers: 3)
ADR Bulletin     Open Access   (Followers: 6)
Advances in Developing Human Resources     Hybrid Journal   (Followers: 23)
Advances in Economics and Business     Open Access   (Followers: 11)
AfricaGrowth Agenda     Full-text available via subscription   (Followers: 1)
African Affairs     Hybrid Journal   (Followers: 59)
African Development Review     Hybrid Journal   (Followers: 33)
African Journal of Business and Economic Research     Full-text available via subscription   (Followers: 1)
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: 11)
Akademika : Journal of Southeast Asia Social Sciences and Humanities     Open Access   (Followers: 5)
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: 158)
American Journal of Business     Hybrid Journal   (Followers: 16)
American Journal of Business and Management     Open Access   (Followers: 53)
American Journal of Business Education     Open Access   (Followers: 10)
American Journal of Economics and Business Administration     Open Access   (Followers: 26)
American Journal of Economics and Sociology     Hybrid Journal   (Followers: 28)
American Journal of Evaluation     Hybrid Journal   (Followers: 13)
American Journal of Finance and Accounting     Hybrid Journal   (Followers: 20)
American Journal of Health Economics     Full-text available via subscription   (Followers: 12)
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: 25)
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: 28)
Annals of Operations Research     Hybrid Journal   (Followers: 8)
Annual Review of Economics     Full-text available via subscription   (Followers: 30)
Applied Developmental Science     Hybrid Journal   (Followers: 3)
Applied Economics     Hybrid Journal   (Followers: 48)
Applied Economics Letters     Hybrid Journal   (Followers: 29)
Applied Economics Quarterly     Full-text available via subscription   (Followers: 10)
Applied Financial Economics     Hybrid Journal   (Followers: 23)
Applied Mathematical Finance     Hybrid Journal   (Followers: 7)
Applied Stochastic Models in Business and Industry     Hybrid Journal   (Followers: 5)
Arab Economic and Business Journal     Open Access   (Followers: 3)
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: 2)
ASEAN Economic Bulletin     Full-text available via subscription   (Followers: 5)
Asia Pacific Business Review     Hybrid Journal   (Followers: 6)
Asia Pacific Journal of Human Resources     Hybrid Journal   (Followers: 321)
Asia Pacific Viewpoint     Hybrid Journal   (Followers: 1)
Asia-Pacific Journal of Business Administration     Hybrid Journal   (Followers: 3)
Asia-Pacific Journal of Operational Research     Hybrid Journal   (Followers: 3)
Asia-Pacific Management and Business Application     Open Access  
Asian Business Review     Open Access   (Followers: 2)
Asian Case Research Journal     Hybrid Journal   (Followers: 1)
Asian Development Review     Open Access   (Followers: 14)
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: 4)
Asian Journal of Business Ethics     Hybrid Journal   (Followers: 7)
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)
Atlantic Economic Journal     Hybrid Journal   (Followers: 15)
Australasian Journal of Regional Studies, The     Full-text available via subscription   (Followers: 2)
Australian Cottongrower, The     Full-text available via subscription   (Followers: 1)
Australian Economic Papers     Hybrid Journal   (Followers: 29)
Australian Economic Review     Hybrid Journal   (Followers: 6)
Australian Journal of Maritime and Ocean Affairs     Hybrid Journal   (Followers: 10)
Balkan Region Conference on Engineering and Business Education     Open Access   (Followers: 1)
Baltic Journal of Real Estate Economics and Construction Management     Open Access   (Followers: 1)
Banks in Insurance Report     Hybrid Journal   (Followers: 1)
BBR - Brazilian Business Review     Open Access   (Followers: 4)
Benchmarking : An International Journal     Hybrid Journal   (Followers: 11)
Benefit : Jurnal Manajemen dan Bisnis     Open Access  
BER : Consumer Confidence Survey     Full-text available via subscription   (Followers: 4)
BER : Economic Prospects : An Executive Summary     Full-text available via subscription  
BER : Economic Prospects : Full Survey     Full-text available via subscription   (Followers: 2)
BER : Intermediate Goods Industries Survey     Full-text available via subscription   (Followers: 1)
BER : Manufacturing Survey : Full Survey     Full-text available via subscription   (Followers: 2)
BER : Motor Trade Survey     Full-text available via subscription   (Followers: 1)
BER : Retail Sector Survey     Full-text available via subscription   (Followers: 2)
BER : Retail Survey : Full Survey     Full-text available via subscription   (Followers: 2)
BER : Survey of Business Conditions in Building and Construction : An Executive Summary     Full-text available via subscription   (Followers: 4)
BER : Survey of Business Conditions in Manufacturing : An Executive Summary     Full-text available via subscription   (Followers: 3)
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: 2)
BER : Wholesale Sector Survey     Full-text available via subscription   (Followers: 1)
Berkeley Business Law Journal     Free   (Followers: 10)
Bio-based and Applied Economics     Open Access   (Followers: 1)
Biodegradation     Hybrid Journal   (Followers: 1)
Biology Direct     Open Access   (Followers: 7)
Black Enterprise     Full-text available via subscription  
Board & Administrator for Administrators only     Hybrid Journal  
Border Crossing : Transnational Working Papers     Open Access   (Followers: 2)
Briefings in Real Estate Finance     Hybrid Journal   (Followers: 5)
British Journal of Industrial Relations     Hybrid Journal   (Followers: 35)
Brookings Papers on Economic Activity     Open Access   (Followers: 48)
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: 7)
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: 18)
Business & Information Systems Engineering     Hybrid Journal   (Followers: 5)
Business & Society     Hybrid Journal   (Followers: 9)
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: 17)
Business and Management Studies     Open Access   (Followers: 9)
Business and Politics     Hybrid Journal   (Followers: 6)
Business and Professional Communication Quarterly     Hybrid Journal   (Followers: 7)
Business and Society Review     Hybrid Journal   (Followers: 5)
Business Economics     Hybrid Journal   (Followers: 6)
Business Ethics: A European Review     Hybrid Journal   (Followers: 16)
Business Horizons     Hybrid Journal   (Followers: 9)
Business Information Review     Hybrid Journal   (Followers: 14)
Business Management and Strategy     Open Access   (Followers: 43)
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: 18)
Business, Peace and Sustainable Development     Full-text available via subscription   (Followers: 3)
Bustan     Hybrid Journal   (Followers: 1)
Cadernos EBAPE.BR     Open Access   (Followers: 1)
Cambridge Journal of Economics     Hybrid Journal   (Followers: 58)
Cambridge Journal of Regions, Economy and Society     Hybrid Journal   (Followers: 11)
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: 28)
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: 12)
Case Studies in Business and Management     Open Access   (Followers: 9)
CBU International Conference Proceedings     Open Access   (Followers: 1)
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: 16)
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: 17)
China Economic Journal: The Official Journal of the China Center for Economic Research (CCER) at Peking University     Hybrid Journal   (Followers: 10)
China Economic Review     Hybrid Journal   (Followers: 9)
China Finance Review International     Hybrid Journal   (Followers: 5)
China Nonprofit Review     Hybrid Journal   (Followers: 3)
China perspectives     Open Access   (Followers: 11)
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: 24)
Compensation & Benefits Review     Hybrid Journal   (Followers: 7)
Competition & Change     Hybrid Journal   (Followers: 10)
Competitive Intelligence Review     Hybrid Journal   (Followers: 2)
Competitiveness Review : An International Business Journal incorporating Journal of Global Competitiveness     Hybrid Journal   (Followers: 6)
Computational Economics     Hybrid Journal   (Followers: 9)
Computational Mathematics and Modeling     Hybrid Journal   (Followers: 8)
Computer Law & Security Review     Hybrid Journal   (Followers: 16)
Computers & Operations Research     Hybrid Journal   (Followers: 10)
Construction Innovation: Information, Process, Management     Hybrid Journal   (Followers: 14)
Contemporary Wales     Full-text available via subscription   (Followers: 3)
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: 4)
Creative and Knowledge Society     Open Access   (Followers: 10)
Creative Industries Journal     Hybrid Journal   (Followers: 9)
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: 9)
De Economist     Hybrid Journal   (Followers: 12)
Decision Analysis     Full-text available via subscription   (Followers: 10)
Decision Sciences     Hybrid Journal   (Followers: 17)
Decision Support Systems     Hybrid Journal   (Followers: 16)
Defence and Peace Economics     Hybrid Journal   (Followers: 18)
der markt     Hybrid Journal   (Followers: 1)
Desenvolvimento em Questão     Open Access  

        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  [3048 journals]
  • Leveraging deep learning with LDA-based text analytics to detect
           automobile insurance fraud
    • Abstract: Publication date: Available online 13 November 2017
      Source:Decision Support Systems
      Author(s): Yibo Wang, Wei Xu
      Automobile insurance fraud represents a pivotal percentage of property insurance companies' costs and affects the companies' pricing strategies and social economic benefits in the long term. Automobile insurance fraud detection has become critically important for reducing the costs of insurance companies. Previous studies on automobile insurance fraud detection examined various numeric factors, such as the time of the claim and the brand of the insured car. However, the textual information in the claims has rarely been studied to analyze insurance fraud. This paper proposes a novel deep learning model for automobile insurance fraud detection that uses Latent Dirichlet Allocation (LDA)-based text analytics. In our proposed method, LDA is first used to extract the text features hiding in the text descriptions of the accidents appearing in the claims, and deep neural networks then are trained on the data, which include the text features and traditional numeric features for detecting fraudulent claims. Based on the real-world insurance fraud dataset, our experimental results reveal that the proposed text analytics-based framework outperforms a traditional one. Furthermore, the experimental results show that the deep neural networks outperform widely used machine learning models, such as random forests and support vector machine. Therefore, our proposed framework that combines deep neural networks and LDA is a suitable potential tool for automobile insurance fraud detection.

      PubDate: 2017-11-15T16:49:14Z
  • Rebuilding sample distributions for small dataset learning
    • Abstract: Publication date: Available online 3 November 2017
      Source:Decision Support Systems
      Author(s): Der-Chiang Li, Wu-Kuo Lin, Chien-Chih Chen, Hung-Yu Chen, Liang-Sian Lin
      Over the past few decades, a few learning algorithms have been proposed to extract knowledge from data. The majority of these algorithms have been developed with the assumption that training sets can denote populations. When the training sets contain only a few properties of their populations, the algorithms may extract minimal and/or biased knowledge for decision makers. This study develops a systematic procedure based on fuzzy theories to create new training sets by rebuilding the possible sample distributions, where the procedure contains new functions that estimate domains and a sample generating method. In this study, two real cases of a leading company in the thin film transistor liquid crystal display (TFT-LCD) industry are examined. Two learning algorithms—a back-propagation neural network and support vector regression—are employed for modeling, and two sample generation approaches—bootstrap aggregating (bagging) and the synthetic minority over-sampling technique (SMOTE)—are employed to compare the accuracy of the models. The results indicate that the proposed method outperforms bagging and the SMOTE with the greatest amount of statistical support.

      PubDate: 2017-11-09T06:31:21Z
  • A Tabu search heuristic for smoke term curation in safety defect discovery
    • Abstract: Publication date: Available online 24 October 2017
      Source:Decision Support Systems
      Author(s): David M. Goldberg, Alan S. Abrahams
      The ability to detect and rapidly respond to the presence of safety defects is vital to firms and to regulatory agencies. In this paper, we employ a text mining methodology to generate industry-specific “smoke terms” for identifying these defects in the countertop appliances and over-the-counter medicine industries. Building upon prior work, we propose several methodological improvements to enhance the precision of our industry-specific terms. First, we replace the subjective manual curation of these terms with an automated Tabu search algorithm, which provides a statistically significant improvement over a sample of human-curated lists. Contrary to the assumptions of prior work, we find that shorter, targeted smoke term lists produce superior precision. Second, we incorporate non-textual review features to enhance the performance of these smoke term lists. In total, we find greater than a twofold improvement over typical human-curated lists. As safety surveillance is vital across industries, our method has great potential to assist firms and regulatory agencies in identifying and responding quickly to safety defects.

      PubDate: 2017-10-26T06:09:41Z
  • Predictive analytics and disused railways requalification: insights from a
           Post Factum Analysis perspective
    • Abstract: Publication date: Available online 24 October 2017
      Source:Decision Support Systems
      Author(s): Krzysztof Ciomek, Valentina Ferretti, Miłosz Kadziński
      Strategic decision making problems in the public policy domain typically involve the comparison of competing options by different stakeholders. This paper considers a real case study oriented toward ranking potential actions for the regeneration of disused railways in Italy. The study involves multiple conflicting criteria such as an~expected duration of construction work, costs, a number of potential users, and new green areas. Within this context, we demonstrate that Post Factum Analysis (PFA) coupled with Decision Aiding supports the development of robust recommendations. The role of PFA is to highlight how the actions’ performances need to be modified so that the recommendation is changed in a desired way. In particular, it highlights the minimal improvements that would warrant the feasibility of a~currently impossible outcome (e.g., achieving a better position in the ranking) or the maximal deteriorations that alternatives can afford to maintain a target result (e.g., not losing their advantage over some other options). The use of a focus group with both experts and participants in the decision making process provided insights on how PFA can support: (i) the creation of arguments in favour or against the respective options under analysis, (ii) understanding of the results’ sensitivity with respect to possible changes in the performances assigned to action on different criteria, (iii) a better informed discussion about the results among the participants in the process, and (iv) the development of new/better alternatives.

      PubDate: 2017-10-26T06:09:41Z
  • Academic paper recommender system using multilevel simultaneous citation
    • Abstract: Publication date: Available online 21 October 2017
      Source:Decision Support Systems
      Author(s): Jieun Son, Seoung Bum Kim
      Researchers typically need to filter several academic papers to find those relevant to their research. This filtering is cumbersome and time-consuming because the number of published academic papers is growing exponentially. Some researchers have focused on developing better recommender systems for academic papers by using citation analysis and content analysis. Most traditional content analysis is implemented using a keyword matching process, and thus it cannot consider the semantic contexts of items. Further, citation analysis-based techniques rely on the number of links directly citing or being cited in a single-level network. Consequently, it may be difficult to recommend the appropriate papers when the paper of interest does not have enough citation information. To address these problems, we propose a recommendation system for academic papers that combines citation analysis and network analysis. The proposed method is based on multilevel citation networks that compare all the indirectly linked papers to the paper of interest to inspect the structural and semantic relationships among them. Thus, the proposed method tends to recommend informative and useful papers related to both the research topic and the academic theory. The comparison results based on real data showed that the proposed method outperformed the Google Scholar and SCOPUS algorithms.

      PubDate: 2017-10-26T06:09:41Z
  • Using contextual features and multi-view ensemble learning in product
           defect identification from online discussion forums
    • 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
  • Workforce management in omnichannel service centers with heterogeneous
           channel response urgencies
    • Abstract: Publication date: Available online 19 October 2017
      Source:Decision Support Systems
      Author(s): Noyan Ilk, Michael Brusco, Paulo Goes
      Workforce staffing and assignment decisions are of critical importance for meeting the challenge of minimizing operational costs while providing satisfactory customer service. These decisions are particularly challenging for omnichannel service centers, where customers can request services via different communication channels (e.g., phone, e-mail, live-chat, social media) that have different service quality and response requirements. We present a formulation of the omnichannel workforce management problem that accounts for variations in response urgencies of different channels as well as diminishing agent performances due to channel switching. We develop an algorithm that efficiently provides solutions for this problem and determines the number and channel allocation of service agents within the service center. Through numerical experiments, we study the performance of the algorithm among various service center configurations with equal cost characteristics. The results indicate that the proposed algorithm can identify service center structures that outperform many alternative structures, including those commonly-adopted in the real-world.

      PubDate: 2017-10-26T06:09:41Z
  • Evaluating the effect of best practices for business process redesign: An
           evidence-based approach based on process mining techniques
    • Abstract: Publication date: Available online 18 October 2017
      Source:Decision Support Systems
      Author(s): Minsu Cho, Minseok Song, Marco Comuzzi, Sooyoung Yoo
      The management of business processes in modern times is rapidly shifting towards being evidence-based. Business process evaluation indicators tend to focus on process performance only, neglecting the definition of indicators to evaluate other concerns of interest in different phases of the business process lifecycle. Moreover, they usually do not discuss specifically which data must be collected to calculate indicators and whether collecting these data is feasible or not. This paper proposes a business process assessment framework focused on the process redesign lifecycle phase and tightly coupled with process mining as an operational framework to calculate indicators. The framework includes process performance indicators and indicators to assess whether process redesign best practices have been applied and to what extent. Both sets of indicators can be calculated using standard process mining functionality. This, implicitly, also defines what data must be collected during process execution to enable their calculation. The framework is evaluated through case studies and a thorough comparison against other approaches in the literature.

      PubDate: 2017-10-26T06:09:41Z
  • Integrated framework for profit-based feature selection and SVM
           classification in credit scoring
    • Abstract: Publication date: Available online 18 October 2017
      Source:Decision Support Systems
      Author(s): Sebastián Maldonado, Cristián Bravo, Julio López, Juan Pérez
      In this paper, we propose a profit-driven approach for classifier construction and simultaneous variable selection based on linear Support Vector Machines. The main goal is to incorporate business-related information such as the variable acquisition costs, the Type I and II error costs, and the profit generated by correctly classified instances, into the modeling process. Our proposal incorporates a group penalty function in the SVM formulation in order to penalize the variables simultaneously that belong to the same group, assuming that companies often acquire groups of related variables for a given cost rather than acquiring them individually. The proposed framework was studied in a credit scoring problem for a Chilean bank, and led to superior performance with respect to business-related goals.

      PubDate: 2017-10-18T17:04:09Z
  • Automatic trading method based on piecewise aggregate approximation and
           multi-swarm of improved self-adaptive particle swarm optimization with
    • Abstract: Publication date: Available online 17 October 2017
      Source:Decision Support Systems
      Author(s): Rodrigo C. Brasileiro, Victor L.F. Souza, Adriano L.I. Oliveira
      Financial time series represent the stock prices over time and exhibit behavior similar to a data stream. Many works report on the use of data mining techniques to predict the future direction of stock prices and to discover patterns in the time series data to provide decision support for trading operations. Traditional optimization methods do not take into account the possibility that the function to be optimized, namely, the final financial balance for operations considering some stock, may have multiple peaks, i.e., be represented by multimodal functions. However, multimodality is a known feature of real-world financial time series optimization problems. To deal with this issue, this article proposes the PAA-MS-IDPSO-V approach (Piecewise Aggregate Approximation - Multi-Swarm of Improved Self-adaptive Particle Swarm Optimization with Validation). The proposed method aims to find patterns in financial time series to support investment decisions. The approach uses multi-swarms to obtain a better particle initialization for the final optimization phase since it aims to tackle multimodal problems. Furthermore, it uses a validation set with early stopping to avoid overfitting. The patterns discovered by the method are used together with investment rules to support decisions and thus help investors to maximize the profit in their operations in the stock market. The experiments reported in this paper compare the results obtained by the proposed model with the Buy-and-Hold, PAA-IDPSO approaches and another approach found in the literature. We report on experiments conducted with S&P100 index stocks and using the Friedman Non-Parametric Test with the Nemenyi post-hoc Test both with 95% confidence level. The results show that the proposed model outperformed the competing methods and was able to considerably reduce the variance for all stocks.

      PubDate: 2017-10-18T17:04:09Z
  • The platform shapes the message: How website design affects abstraction
           and valence of online consumer reviews
    • Abstract: Publication date: Available online 16 October 2017
      Source:Decision Support Systems
      Author(s): Goele Aerts, Tim Smits, Peeter Verlegh
      Online consumer reviews provide relevant information about products and services for consumers. In today's networked age, the online consumer review platform market is hyper-competitive. These platforms can easily change different design characteristics to get more reviewers and to nudge reviewers to deliver higher quality reviews. This study explored the relation between online consumer review platforms' design characteristics and the reviewers' construal level. A psycholinguistic coding scheme was used to assess which social and physical design characteristics impact the language abstraction in accompanying online consumer reviews. To this end, we content analyzed reviews of services and products posted on eight different online consumer review platforms (N =400). This resulted in a number of key design characteristics (e.g., reviewer identification, reviewer status, order of instructions and length instructions) that led to a decrease in language abstraction used in online consumer reviews. Moreover, results showed that language abstraction mediated the relationship between the four design characteristics and valence. The findings and their broader theoretical, methodological and practical implications are discussed. Online consumer review platforms could capitalize on our findings in adaptive design choices.

      PubDate: 2017-10-18T17:04:09Z
  • Decision support from financial disclosures with deep neural networks and
           transfer learning
    • Abstract: Publication date: Available online 9 October 2017
      Source:Decision Support Systems
      Author(s): Mathias Kraus, Stefan Feuerriegel
      Company disclosures greatly aid in the process of financial decision-making; therefore, they are consulted by financial investors and automated traders before exercising ownership in stocks. While humans are usually able to correctly interpret the content, the same is rarely true of computerized decision support systems, which struggle with the complexity and ambiguity of natural language. A possible remedy is represented by deep learning, which overcomes several shortcomings of traditional methods of text mining. For instance, recurrent neural networks, such as long short-term memories, employ hierarchical structures, together with a large number of hidden layers, to automatically extract features from ordered sequences of words and capture highly non-linear relationships such as context-dependent meanings. However, deep learning has only recently started to receive traction, possibly because its performance is largely untested. Hence, this paper studies the use of deep neural networks for financial decision support. We additionally experiment with transfer learning, in which we pre-train the network on a different corpus with a length of 139.1 million words. Our results reveal a higher directional accuracy as compared to traditional machine learning when predicting stock price movements in response to financial disclosures. Our work thereby helps to highlight the business value of deep learning and provides recommendations to practitioners and executives.

      PubDate: 2017-10-11T16:43:19Z
  • How Can Online Marketplaces Reduce Rating Manipulation' A New Approach
           on Dynamic Aggregation of Online Ratings
    • Abstract: Publication date: Available online 7 October 2017
      Source:Decision Support Systems
      Author(s): Olga Ivanova, Michael Scholz
      Retailers’ incentives to manipulate online ratings can undermine consumers’ trust in online marketplaces. Finding ways to avoid fake ratings has become a fundamental problem. Most marketplaces update product ratings immediately, i.e., display new ratings as soon as they are submitted. Some platforms have proposed to reduce the frequency of rating updates, as hiding ratings for a certain amount of time allows identifying and eliminating bursts of suspicious ratings. Reducing the update frequency also allows aggregating ratings and displaying only a summary statistic (e.g., mean of ratings). Although such aggregation helps to reduce the amount of fake ratings, as multiple fake ratings get represented by only one value, it might also distort legitimate ratings from real customers and hence have negative impact on honest retailers. In the present study, we propose and evaluate a novel method that instead of displaying every new rating immediately, aggregates a sequence of most recent ratings to k-values, with k determined dynamically based on the distribution of the recent ratings. In a simulation, we demonstrate that our proposed method outperforms state-of-the-art aggregation methods – it effectively reduces the impact of fake ratings on sales, and at the same time only marginally affects sales of honest retailers. Our proposed method can be easily integrated in online rating systems and can be especially used for designing fraud-resistant ranking algorithms.

      PubDate: 2017-10-11T16:43:19Z
  • A cross-domain recommender system with consistent information transfer
    • Abstract: Publication date: Available online 6 October 2017
      Source:Decision Support Systems
      Author(s): Qian Zhang, Dianshuang Wu, Jie Lu, Feng Liu, Guangquan Zhang
      Recommender systems provide users with personalized online product and service recommendations and are a ubiquitous part of today's online entertainment smorgasbord. However, many suffer from cold-start problems due to a lack of sufficient preference data, and this is hindering their development. Cross-domain recommender systems have been proposed as one possible solution. These systems transfer knowledge from one domain that has adequate preference information to another domain that does not. The outlook for cross-domain recommendation is promising, but existing methods cannot ensure the knowledge extracted from the source domain is consistent with the target domain, which may impact the accuracy of the recommendations. To address this challenging issue, we propose a cross-domain recommender system with consistent information transfer (CIT). Knowledge consistency is based on user and item latent groups, and domain adaptation techniques are used to map and adjust these groups in both domains to maintain consistency during the transfer learning process. Experiments were conducted on five real-world datasets in three categories: movies, books, and music. The results for nine cross-domain recommendation tasks show that CIT outperforms five benchmarks and increases the accuracy of recommendations in the target domain, especially with sparse data. Practically, our proposed method is applied into a telecom product recommender system and a business partner recommender system (Smart BizSeeker) to enhance personalized decision making for both businesses and individual customers.

      PubDate: 2017-10-11T16:43:19Z
  • Test sequencing for sequential system diagnosis with precedence
           constraints and imperfect tests
    • Abstract: Publication date: Available online 3 October 2017
      Source:Decision Support Systems
      Author(s): Wenchao Wei, Hongbo Li, Roel Leus
      We study sequential system testing with the objective of minimizing the total expected testing costs. The goal is to discover the state of a system that consists of a set of independent components. The state of the system depends on the states of the individual components and is classified as working if at least a pre-specified number of components are working, otherwise it is said to be down. During the diagnostic testing procedure, components are tested one by one, in a pre-specified order. The resulting test sequencing problem is NP-hard with general precedence constraints even when the tests are perfect, in which case a component test always reports the correct state of the component. In this work, we will also consider the additional complication that tests can be imperfect, meaning that a test can report a component to be working when it is actually down, and vice versa. We develop a tabu search algorithm together with a simulation-based evaluation technique that incorporates importance sampling to find high-quality solutions within limited runtimes.

      PubDate: 2017-10-04T00:57:49Z
  • The added value of social media data in B2B customer acquisition systems:
           A real-life experiment
    • Abstract: Publication date: Available online 1 October 2017
      Source:Decision Support Systems
      Author(s): Matthijs Meire, Michel Ballings, Dirk Van den Poel
      Business-to-business organizations and scholars are becoming increasingly aware of the possibilities social media and predictive analytics offer. Despite the interest in social media, only few have analyzed the impact of social media on the sales process. This paper takes a quantitative view to examine the added value of Facebook data in the customer acquisition process. In order to do so, we devise a customer acquisition decision support system to qualify prospects as potential customers, and incorporate commercially purchased prospecting data, website data and Facebook data. Our system is subsequently used by Coca Cola Refreshments Inc. (CCR) to generate calling lists of beverage serving outlets, ranked by their likelihood of becoming a customer. In this paper we report the results, in terms of prospect-to-customer conversion, of a real-life experiment encompassing nearly 9000 prospects. The results show that Facebook is the most informative data source to qualify prospects, and is complementary with the other data sources in that it further improves predictive performance. We contribute to literature in that we are the first to investigate the effectiveness of social media information in acquiring B2B-customers. Our results imply that Facebook data challenge current best practices in customer acquisition.

      PubDate: 2017-10-04T00:57:49Z
  • On a participation structure that ensures representative prices in
           prediction markets
    • Abstract: Publication date: Available online 1 October 2017
      Source:Decision Support Systems
      Author(s): Arthur Carvalho
      The logarithmic market scoring rule (LMSR) is now the de facto market-maker mechanism for prediction markets. We show how LMSR can have more representative final prices by simply imposing a participation structure where the market proceeds in rounds and, in each round, traders can only trade up to a fixed number of contracts. Focusing on markets over binary outcomes, we prove that under such a participation structure, the market price converges after a finite number of rounds to the median of traders' private information for an odd number of traders, and to a point in the median interval for an even number of traders. Thus, the final market price effectively represents all agents' private information since those equilibria are measures of central tendency. We also show that when traders use market price data to revise their private information, the aforementioned equilibrium prices do not change for a broad class of learning methods.

      PubDate: 2017-10-04T00:57:49Z
  • Information representation in decision making: The impact of cognitive
           style and depletion effects
    • Abstract: Publication date: Available online 28 September 2017
      Source:Decision Support Systems
      Author(s): Ayşegül Engin, Rudolf Vetschera
      Although the literature on information representation in decision support has argued for a long time that the way in which information is presented to decision makers should fit both task characteristics and the cognitive style of decision makers, the latter aspect has received much less attention in empirical research. Most studies that took into account cognitive style used rather general instruments to measure it, which do not focus on the specifics of managerial decision making. In this paper, we describe an experiment that uses an instrument specifically developed for a managerial context to study the relationship between cognitive style and decision performance when using tabular or graphical representations. We also take into account that having to deal with a misfitting information representation depletes cognitive resources, and thus might not only impede the solution of the current problem, but also impact subsequent problems. Our results confirm that a mismatch between information representation and cognitive style indeed has effects that last beyond the solution of the current decision problem.

      PubDate: 2017-10-04T00:57:49Z
  • Counterfeit product detection: Bridging the gap between design science and
           behavioral science in information systems research
    • Abstract: Publication date: Available online 21 September 2017
      Source:Decision Support Systems
      Author(s): Hayden Wimmer, Victoria Y. Yoon
      In IS research, there is a dichotomy where design science and behavioral science are distinct research paradigms. IS researchers should view these paradigms as complementary with research drawing upon the strengths of both, yet few have done so. This work demonstrates how design science and behavioral science can be united in IS research via counterfeit product detection based on product reviews in an online marketplace. Product authenticity in the online marketplace is a common issue plaguing consumers. The decision process involved in determining product authenticity is lengthy and complex. Despite the pressing need for an automatic authenticity rating system for online shopping, little research has been done to develop such a system and assess its effects on consumer purchase behavior. To respond to this need, our study develops a design artifact, called OnCDS, to automatically calculate the likelihood that a product is counterfeit based on online customer reviews. Drawing upon lexicon-based sentiment analysis approaches and TF-IDF as kernel theories for our design, we employ web scraping, natural language processing, and topic analysis methods to process customer reviews and calculate the counterfeit score of a product. In assessing the effects of OnCDS on consumer behavior, we develop a research model that encompasses trust and perceived risk based on the valence framework. Results show that our design artifact's efficacy is validated and that the counterfeit score affects perceived risk and trust, which in turn influences attitude toward purchase.

      PubDate: 2017-09-25T20:30:56Z
  • Development and evaluation of a continuous-time Markov chain model for
           detecting and handling data currency declines
    • Abstract: Publication date: Available online 21 September 2017
      Source:Decision Support Systems
      Author(s): Yuval Zak, Adir Even
      Data currency declines, caused by recorded data values becoming outdated, can damage the usability and accountability of data resources. Detecting and updating outdated values may improve data currency and reduce the associated damage, but such efforts may be costly and cannot always be justified. This study models currency decline scenarios using a continuous-time Markov chain stochastic process with a finite number of states, each reflecting a valid data value. The model considers state transition probabilities, transition time distributions, and the tradeoff between the damage associated with outdated data and the cost of reacquisition. The proposed formulation permits the currency level to be estimated without having to rely on a baseline for comparison, as well as the prediction of future currency declines, assessment of their accumulated damage, and optimization of the timing of cost-effective data auditing and reacquisition. The study introduces a comprehensive evaluation of the proposed model, using a large real-world dataset relating to the handling of insurance claims over multiple time periods. The evaluation results highlight the applicability of the model, and its potential contribution to proactive data quality management and cost-effective handling of currency declines.

      PubDate: 2017-09-25T20:30:56Z
  • Improving cognitive effectiveness of business process diagrams with
           opacity-driven graphical highlights
    • Abstract: Publication date: Available online 20 September 2017
      Source:Decision Support Systems
      Author(s): Gregor Jošt, Jernej Huber, Marjan Heričko, Gregor Polančič
      In order to facilitate the communication between the stakeholders, business process diagrams must be easy to understand. This is challenging to achieve, since they can become large and complex. In our previous work, we proposed Opacity-Driven Graphical Highlights, a novel approach for increasing the cognitive effectiveness of business process diagrams by changing the opacity of graphical elements and provided a prototype implementation of the approach. The goal of this study was to empirically validate if our proposed approach positively impacts cognitive effectiveness of business process diagrams and if the users will find the prototype implementation useful. To this end an experimental research was conducted where speed, ease and accuracy of answering questions were observed along with the perceived usefulness of the prototype. Participants that used Opacity-Driven Graphical Highlights significantly outperformed those that used the conventional approach. We can conclude that using Opacity-Driven Graphical Highlights increases the cognitive effectiveness of business process diagrams, while the corresponding prototype is perceived as being useful.

      PubDate: 2017-09-25T20:30:56Z
  • Getting phished on social media
    • Abstract: Publication date: Available online 19 September 2017
      Source:Decision Support Systems
      Author(s): Arun Vishwanath
      The study experimentally simulated a level-1 social networking-based phishing (SNP) attack, where a phisher using a phony profile attempts to friend an individual on Facebook, and a level-2 SNP attack, where a phisher attempts to extract information directly. The results implicate the use of cognitive shortcuts triggered by the cues afforded in Facebook's interface. Individuals appeared to be using the phisher's friend count as a heuristic for judging the authenticity of a level-1 request. They, thus, responded to a phisher displaying a large friend count even in the absence of a profile picture. Interestingly, the affordance of smartphones used to access social media—an issue that has received little academic attention—increased the odds of considering such requests sevenfold.

      PubDate: 2017-09-25T20:30:56Z
  • Comparing alternatives to account for unobserved heterogeneity in direct
           marketing models
    • Abstract: Publication date: Available online 8 September 2017
      Source:Decision Support Systems
      Author(s): Nadine Schröder, Harald Hruschka
      We are dealing with mailing decisions of a direct marketing company and focus on assessing three alternative approaches to model unobserved heterogeneity, which are based on finite mixtures, continuous mixtures, and a mixture of Dirichlet processes (MDP), respectively. Models are estimated by Markov Chain Monte Carlo (MCMC) simulation. Based on Pseudo Bayes factors (PsBF), we find that a finite mixture model turns out to be superior both to models based on either a MDP or a continuous mixture. Whereas the MDP finds similar estimates compared to the finite mixture approach, estimates of the continuous mixture differ for some variables. According to the finite mixture, type of mailing has an effect on purchase behavior. In addition, some customers show supersaturation effects of mailings. Due to different coefficient estimates, managerial implications differ depending on which model they relate. In particular, a continuous mixture model would recommend more mailings than a finite mixture approach.

      PubDate: 2017-09-13T12:48:09Z
  • A game theoretic analysis of multichannel retail in the context of
    • Abstract: Publication date: Available online 6 September 2017
      Source:Decision Support Systems
      Author(s): Preetam Basu, Shounak Basak, Balram Avittathur, Soumyen Sikdar
      “Showrooming” as a market phenomenon in multichannel retailing has grown in importance over the last few years. Consumers nowadays use the brick-and-mortar store to research about a product before purchasing it online. This leads to the offline stores being converted into showrooms for the online retailers. Therefore, popular notion suggests that showrooming should benefit the online retailer. In this paper, our objective is to analyze multichannel retailing under showrooming and determine the veracity of the popularly held belief. We develop a series of game theoretic models that involve a traditional retailer and an online retailer under showrooming. We determine optimal pricing strategies for each player and also the sales effort expended by the traditional retailer based on the interplay of “power” dynamics, market potential and the impact of showrooming. Our results indicate that profit for the traditional as well as the online retailer decreases with rising levels of showrooming. Hence, high levels of showrooming are not beneficial from the perspective of the online retailer. Thus, contrary to popular intuition, lessening of showrooming benefits not only the traditional retailer but also the online retailer. Nevertheless, from the consumer's point of view showrooming is beneficial as it leads to overall reduction in retail prices. We also analyze the viability of a click-and-mortar model as a strategy of the traditional retailer to counter the threat of showrooming.

      PubDate: 2017-09-07T13:30:44Z
  • A context-aware researcher recommendation system for university-industry
           collaboration on R&D projects
    • Abstract: Publication date: Available online 5 September 2017
      Source:Decision Support Systems
      Author(s): Qi Wang, Jian Ma, Xiuwu Liao, Wei Du
      University-industry collaboration plays an important role in the success of R&D projects. One of the main challenges of university-industry collaboration is the identification of suitable partners. Due to the information asymmetry problem, it is difficult for companies to identify researchers from universities for collaboration on their R&D projects. Various expert recommendation systems (e.g., question responder recommenders and co-author recommenders) have been proposed, but they fail to characterize companies' needs in identifying suitable researchers. This paper proposes a context-aware researcher recommendation system to encourage university-industry collaboration on industrial R&D projects. The system has two modules: an offline preparation module and an online recommendation module. In the offline preparation module, candidate researchers are identified in advance to improve the efficiency of the context-aware recommendation. In the online recommendation module, contextual information (i.e., R&D projects) is captured from a social network platform, and then, candidate researchers are recommended based on a contextual trust analysis model, which combines the expertise relevance, quality, and trust relations of researchers to profile and evaluate candidate researchers for the R&D project collaboration. An offline experiment and a user study are conducted to evaluate the effectiveness of the proposed recommendation system. The results show that the proposed method achieves better performance than the baseline methods.

      PubDate: 2017-09-07T13:30:44Z
  • Early detection of university students with potential difficulties
    • Abstract: Publication date: September 2017
      Source:Decision Support Systems, Volume 101
      Author(s): Anne-Sophie Hoffait, Michaël Schyns
      Using data mining methods, this paper presents a new means of identifying freshmen's profiles likely to face major difficulties to complete their first academic year. Academic failure is a relevant issue at a time when post-secondary education is ever more critical to economic success. We aim at early detection of potential failure using student data available at registration, i.e. school records and environmental factors, with a view to timely and efficient remediation and/or study reorientation. We adapt three data mining methods, namely random forest, logistic regression and artificial neural network algorithms. We design algorithms to increase the accuracy of the prediction when some classes are of major interest. These algorithms are context independent and can be used in different fields. Real data pertaining to undergraduates at the University of Liège (Belgium), illustrates our methodology.

      PubDate: 2017-09-02T02:41:25Z
  • An analytic approach to assessing organizational citizenship behavior
    • Abstract: Publication date: Available online 1 September 2017
      Source:Decision Support Systems
      Author(s): Ozlem Ayaz Arda, Dursun Delen, Ekrem Tatoglu, Selim Zaim
      This study examines the organizational citizenship behavior (OCB) of employees by designing and developing an analytic network process (ANP) methodology. The viability of the proposed methodology is demonstrated via the sales representatives of Beko, a brand name of domestic appliance and consumer electronics giant of Arçelik Inc., controlled by Koç Group. We first develop a conceptual framework based on qualitative research methods – in-depth interviews and focus group sessions. We employ the principles of ANP methodology to examine and discover the inter-relationships among the OCBs. This process results in a descriptive model that encapsulates the findings from both qualitative and analytics methods. Necessity, altruism, departmental, compliance, and independence are the underlying dimensions of OCBs found to be the most influential/important. The key novelty of this study resides in designing and developing a prescriptive analytics (i.e. ANP) methodology to objectively evaluate the OCBs, which is rare in the area of organizational behavior (a managerial field of study that have been dominated by traditional statistical methods), and thus serves as a useful contribution/augmentation to the business/managerial research methods, and also extends the reach/coverage of analytics-based decision support systems research and practice into a new direction.

      PubDate: 2017-09-02T02:41:25Z
  • Solvency prediction for small and medium enterprises in banking
    • Abstract: Publication date: Available online 14 August 2017
      Source:Decision Support Systems
      Author(s): Silvia Figini, Federico Bonelli, Emanuele Giovannini
      This paper describes novel approaches to predict default for SMEs. Multivariate outlier detection techniques based on Local Outlier Factor are proposed to improve the out of sample performance of parametric and non-parametric models for credit risk estimation. The models are tested on a real data set provided by UniCredit Bank. The results at hand confirm that our proposal improves the results in terms of predictive capability and support financial institutions to make decision. Single and ensemble models are compared and in particular, inside parametric models, the generalized extreme value regression model is proposed as a suitable competitor of the logistic regression.

      PubDate: 2017-09-02T02:41:25Z
  • Online to offline (O2O) service recommendation method based on
           multi-dimensional similarity measurement
    • Abstract: Publication date: Available online 10 August 2017
      Source:Decision Support Systems
      Author(s): Yuchen Pan, Desheng Wu, David L. Olson
      With the rapid development of information technology, consumers are able to search for and buy services or products online, and then consume them in an offline store. This emerging ecommerce model is called online to offline (O2O) service, which has attracted business and academic attention. The large number of O2O services on the Internet creates a scalability problem, creating massive but highly sparse matrices relating customers to items purchased. In this paper, we proposed a novel O2O service recommendation method based on multi-dimensional similarity measurements. This approach encompasses three similarity measures: collaborative similarity, preference similarity and trajectory similarity. Experimental results show that a combination of multiple similarity measures performs better than any one single similarity measure. We also find that trajectory similarity performs better than the rating-based similarity metrics (collaborative similarity and preference similarity) in sparse matrices.

      PubDate: 2017-09-02T02:41:25Z
  • Movie aspects, tweet metrics, and movie revenues: The influence of iOS vs.
    • Abstract: Publication date: Available online 8 August 2017
      Source:Decision Support Systems
      Author(s): David Zimbra, Kumar R. Sarangee, Rupinder P. Jindal
      Microblogging word of mouth (MWOM) using Twitter has been found to impact the success of experiential products such as movies. However, the influence of the type of device or platform used for tweeting (iOS or Android) on the relationship between well-established tweet metrics - valence, volume, and time period of tweeting - and movie performance is not yet known. Furthermore, it is not known if users of these platforms differ in the aspects of movies they discuss and how that may influence tweet metrics. In this study, we investigated these gaps by analyzing more than four million tweets for 29 movies from both iOS and Android users and conducted a robustness check on another 8 movies. Results from mixed model estimations show that valence of tweets on Android before a movie's release and volume of tweets on iOS after the release significantly influence the revenues of a movie. Results also show that mentions of director and script are more important in the case of Android users whereas mentions of production and music are more important in the case of iOS users. Finally, results show that it may be more productive for movie studios and advertisers to reach the more prolific Twitter users on Android but relatively newer Twitter users on iOS. These findings have significant implications for movie studios as well as mobile advertisers to target their promotions to these platform users accordingly.

      PubDate: 2017-09-02T02:41:25Z
  • Decision support to customer decrement detection at the early stage for
           theme parks
    • Abstract: Publication date: Available online 2 August 2017
      Source:Decision Support Systems
      Author(s): Yen Chung-en, Chun-Che Huang, Marian (Dan-Wei) Wen, Wang You-Ping
      In recent years, a theme park drives significant attention in tourism industry due to the provision of quality and integrated service, and issuing annual pass cards help the theme park to differentiate long-term customers from short-term ones. Customer Value Analysis is demanded for theme parks to identify potential customers as well as to appraise customer value through the setting of the annual pass. Moreover, customer value often alters from time to time since theme park industry is relevantly competitive and innovation demanded than other industries, and customer preferences are frequently changed. This study provides an early warning system to support the theme park to detect, monitor and analyze the changes of customer value. By applying the aggregated approach based on Rough Set Theory and Recency, Frequency and Monetary architecture, the tourist satisfaction levels can be captured after the aforementioned approach is executed. In addition, the rule comparison approach is contributed to predicting customer behavior from technical viewpoint. This study aims at providing an early correction strategy for the theme park to avoid losing VIP customers and identify latent customers.

      PubDate: 2017-08-03T04:39:01Z
  • Bankruptcy prediction for SMEs using relational data
    • Abstract: Publication date: Available online 18 July 2017
      Source:Decision Support Systems
      Author(s): Ellen Tobback, Tony Bellotti, Julie Moeyersoms, Marija Stankova, David Martens
      Bankruptcy prediction has been a popular and challenging research area for decades. Most prediction models are built using financial figures, stock market data and firm specific variables. We complement such traditional low-dimensional data with high-dimensional data on the company’s directors and managers in the prediction models. This information is used to build a network between small and medium-sized enterprises (SMEs), where two companies are related if they share a director or high-level manager. A smoothed version of the weighted-vote relational neighbour classifier is applied on the network and transforms the relationships between companies into bankruptcy prediction scores, thereby assuming that a company is more likely to file for bankruptcy if one of the related companies in its network has already failed. An ensemble model is built that combines the relational model’s output scores with structured data and is applied on two data sets of Belgian and UK SMEs. We find that the relational model gives improved predictions over a simple financial model when detecting the riskiest firms. The largest performance increase is found when the relational and financial data are combined, confirming the complementary nature of both data types.

      PubDate: 2017-07-22T21:40:49Z
  • Emergency Response Community Effectiveness: A simulation modeler for
           comparing Emergency Medical Services with smartphone-based Samaritan
    • Abstract: Publication date: Available online 14 July 2017
      Source:Decision Support Systems
      Author(s): Michael Khalemsky, David G. Schwartz
      Mobile emergency response applications involving location-based alerts and physical response of networked members increasingly appear on smartphones to address a variety of emergencies. EMS (Emergency Medical Services) administrators, policy makers, and other decision makers need to determine when such systems present an effective addition to traditional Emergency Medical Services. We developed a software tool, the Emergency Response Community Effectiveness Modeler (ERCEM) that accepts parameters and compares the potential smartphone-initiated Samaritan/member response to traditional EMS response for a specific medical condition in a given geographic area. This study uses EMS data from the National EMS Information System (NEMSIS) and analyses geographies based on Rural-Urban Commuting Area (RUCA) and Economic Research Service (ERS) urbanicity codes. To demonstrate ERCEM's capabilities, we input a full year of NEMSIS data documenting EMS response incidents across the USA. We conducted three experiments to explore anaphylaxis, hypoglycemia and opioid overdose events across different population density characteristics, with further permutations to consider a series of potential app adoption levels, Samaritan response behaviors, notification radii, etc. Our model emphasizes how medical condition, prescription adherence levels, community network membership, and population density are key factors in determining the effectiveness of Samaritan-based Emergency Response Communities (ERC). We show how the efficacy of deploying mHealth apps for emergency response by volunteers can be modelled and studied in comparison to EMS. A decision maker can utilize ERCEM to generate a detailed simulation of different emergency response scenarios to assess the efficacy of smartphone-based Samaritan response applications in varying geographic regions for a series of different conditions and treatments.

      PubDate: 2017-07-22T21:40:49Z
  • A systematic literature review and critical assessment of model-driven
           decision support for IT outsourcing
    • Abstract: Publication date: Available online 8 July 2017
      Source:Decision Support Systems
      Author(s): Mohammad Mehdi Rajaeian, Aileen Cater-Steel, Michael Lane
      Information technology outsourcing (ITO) is a widely-adopted strategy for IT governance. The decisions involved in IT outsourcing are complicated. Empirical research confirms that a rational and formalized decision-making process results in better decision outcomes. However, formal and systematic approaches for making ITO decisions appear to be scarce in practice. To support organizational decision-makers involved in IT outsourcing (including cloud sourcing), researchers have suggested several decision support methods. To date there is no comprehensive review and assessment of the research in this domain. In this study 133 model-driven decision support research articles for IT outsourcing and cloud sourcing were identified through a systematic literature review and assessed based on a highly-regarded research framework. An analysis of these 133 research articles suggested a range of Multiple Criteria Decision Making (MCDM), optimization and simulation methods to support different IT outsourcing decisions. Our findings raise concerns about the limited use of reference design theories, and the lack of validation and naturalistic evaluation of the decision support artifacts reported in ITO decision support literature. Based on the review, we provide future research directions, as well as a number of recommendations to enhance the rigor and relevance of ITO Decision Support Systems research.

      PubDate: 2017-07-09T07:29:48Z
  • Invention or incremental improvement' Simulation modeling and
    • Abstract: Publication date: Available online 6 July 2017
      Source:Decision Support Systems
      Author(s): Bin GUO, Peng DING
      This paper explores how firms determine their patenting strategy when faced with different performance situations. Patenting strategy in this study is defined in terms of either engaging more in inventions with more risk and higher profit or in more incremental improvements with less risk and lower profit. We develop two game-theoretical models to analyze how different kinds of performance discrepancies encountered by a firm influence the evolution of the firm’s propensity toward a patenting strategy. Then, an empirical analysis of 1,921 listed companies in China is conducted to test the propositions derived from the two game-theoretical models. The results reveal the decision-making pattern of a firm’s patenting strategy. Specifically, a firm with performance higher than its aspiration will prefer to engage more in invention-type patents, while a firm with lower performance than its aspiration will invest more in incremental improvement patents. Additionally, all else being equal, the patenting strategy more likely to succeed will be more appealing to firms, no matter what kinds of performance gaps they have.

      PubDate: 2017-07-09T07:29:48Z
  • Kernel-based features for predicting population health indices from
           geocoded social media data
    • Abstract: Publication date: Available online 4 July 2017
      Source:Decision Support Systems
      Author(s): Thin Nguyen, Mark E. Larsen, Bridianne O’Dea, Duc Thanh Nguyen, John Yearwood, Dinh Phung, Svetha Venkatesh, Helen Christensen
      When using tweets to predict population health index, due to the large scale of data, an aggregation of tweets by population has been a popular practice in learning features to characterize the population. This would alleviate the computational cost for extracting features on each individual tweet. On the other hand, much information on the population could be lost as the distribution of textual features of a population could be important for identifying the health index of that population. In addition, there could be relationships between features and those relationships could also convey predictive information of the health index. In this paper, we propose mid-level features namely kernel-based features for prediction of health indices of populations from social media data. The kernel-based features are extracted on the distributions of textual features over population tweets and encode the relationships between individual textual features in a kernel function. We implemented our features using three different kernel functions and applied them for two case studies of population health prediction: across-year prediction and across-county prediction. The kernel-based features were evaluated and compared with existing features on a dataset collected from the Behavioral Risk Factor Surveillance System dataset. Experimental results show that the kernel-based features gained significantly higher prediction performance than existing techniques, by up to 16.3%, suggesting the potential and applicability of the proposed features in a wide spectrum of applications on data analytics at population levels.

      PubDate: 2017-07-09T07:29:48Z
  • Lightweight Non-Distance-Bounding Means to Address RFID Relay Attacks
    • Abstract: Publication date: Available online 3 July 2017
      Source:Decision Support Systems
      Author(s): Yuju Tu, Selwyn Piramuthu
      A relay attack is accomplished by simply relaying messages between a prover (e.g., an RFID tag) and a verifier (e.g., an RFID reader) with the goal of convincing the verifier of its close physical proximity to the prover. In almost all relay attack scenarios, the verifier essentially communicates with a prover that is outside the verifier’s read-range. Relay attacks are notorious since they occur without the knowledge of the reader and/or tag, and has the potential to cause damage to honest parties (here, RFID reader and/or tag). Almost all means to address relay attacks in RFID systems to date are based on the proximity check idea that involves the measurement of message round trip times between tag and reader. With the speed of light at play, such measurements need not necessarily be accurate and could result in the false assumption of relay attack absence. Our review of published literature on approaches that use non-distance-based means to address relay attacks revealed ambient conditions’ potential. We critically evaluate ambient conditions and develop a lightweight mutual authentication protocol that is based on magnetometer readings to address relay attacks.

      PubDate: 2017-07-09T07:29:48Z
  • How e-WOM and local competition drive local retailers' decisions about
           daily deal offerings
    • Abstract: Publication date: Available online 1 July 2017
      Source:Decision Support Systems
      Author(s): Xue Bai, James R. Marsden, William T. Ross, Gang Wang
      Local retailers considering offering daily deals must take into account possible impacts of both electronic-word-of-mouth (e-WOM) and local competition. However, how e-WOM, local competition, and their interactions affect local retailers' decisions to offer daily deals remains unclear. Here we examine these effects utilizing a data set that contains details of daily deals, online reviews, and local competition measures for restaurants in the Chicago area. With a propensity score matching (PSA) method, we show: 1) local retailers with high ratings and high number of reviews were more likely to initiate daily deals; 2) local retailers in an area with a low level of local competition were more likely to initiate daily deals; and 3) the strength and direction of the impact of e-WOM depend on the level of local competition. Our results enhance understanding of local retailers' decisions to offer daily deals and yield important implications related to daily deal sites.

      PubDate: 2017-07-09T07:29:48Z
  • Understanding the determinants of online review helpfulness: A
           meta-analytic investigation
    • Abstract: Publication date: Available online 29 June 2017
      Source:Decision Support Systems
      Author(s): Hong Hong, Di Xu, G. Alan Wang, Weiguo Fan
      Online consumer reviews can help customers reduce uncertainty and risks faced in online shopping. However, the studies examining the determinants of perceived review helpfulness produce mixed findings. We review extant research about the determinant factors of perceived online review helpfulness. All review related determinants (i.e., review depth, review readability, linear review rating, quadratic review rating, review age) and two reviewer related determinants (i.e., reviewer information disclosure and reviewer expertise) are found to have inconsistent conclusions on how they affect perceived review helpfulness. We conduct a meta-analysis to examine those determinant factors in order to reconcile the contradictory findings about their influence on perceived review helpfulness. The meta-analysis results affirm that review depth, review age, reviewer information disclosure, and reviewer expertise have positive influences on review helpfulness. Review readability and review rating are found to have no significant influence on review helpfulness. Moreover, we find that helpfulness measurement, online review platform, and product type are the three factors that cause mixed findings in extant research.

      PubDate: 2017-07-09T07:29:48Z
  • Multi-objective optimization based ranking prediction for cloud service
    • Abstract: Publication date: Available online 28 June 2017
      Source:Decision Support Systems
      Author(s): Shuai Ding, Chengyi Xia, Chengjiang Wang, Desheng Wu, Youtao Zhang
      Performing effective ranking prediction for cloud services can help customers make prompt decisions when they are confronted by a large number of choices. This can also enhance web service user satisfaction levels. Improving ranking prediction of QoS-based services continues to be an active topic of research in cloud service recommendation. Most service recommendation algorithms focus on prediction accuracy, ignoring diversity, which also may be an important consideration. In this paper we view service recommendation as a multi-objective optimization problem, and give two modified ranking prediction and recommendation algorithms that simultaneously consider accuracy and diversity. Existing algorithm recommendations can be made much more diverse by adjusting weights on service origin and substantially reducing the risk of inappropriate recommendations. Our experiments show that the algorithms we propose can yield greater diversity without greatly sacrificing prediction accuracy.

      PubDate: 2017-07-09T07:29:48Z
  • Increasing firm agility through the use of data analytics: The role of fit
    • Abstract: Publication date: Available online 28 June 2017
      Source:Decision Support Systems
      Author(s): Maryam Ghasemaghaei, Khaled Hassanein, Ofir Turel
      Agility, which refers to a dynamic capability within firms to identify and effectively respond to threats and opportunities with speed, is considered as a main business imperative in modern business environments. While there is some evidence that information technology (IT) capabilities can help organizations to be more agile, studies have reported mixed findings regarding such effects. In this study, we identify the conditions under which IT capabilities translate into agility gains. We focus on a specific and critical IT capability, the use of data analytics, which is often leveraged by firms to improve decision making and achieve agility gains. We leverage dynamic capability theory to understand the influence of data analytics use as a lower-order dynamic capability on firm agility as a higher-order dynamic capability. We also draw on the fit perspective to suggest that this impact will only accrue if there is a high degree of fit between several elements that are closely related to the use of data analytics tools within firms including the tools themselves, the users, the firm tasks, and the data. The proposed research model is empirically validated using survey data from 215 senior IT professionals confirming the importance of high levels of fit between data analytics tools and key related elements. The findings provide the understanding of the impacts of data analytics use on firm agility, while also providing guidance to managers on how they could better leverage the use of such technologies. These findings could be more broadly used to inform the effective use of other forms of IT in organizations.

      PubDate: 2017-07-09T07:29:48Z
  • The time-varying nature of social media sentiments in modeling stock
    • Abstract: Publication date: Available online 22 June 2017
      Source:Decision Support Systems
      Author(s): Chi-San Ho, Paul Damien, Bin Gu, Prabhudev Konana
      The broad aim of this paper is to answer the following query: is the relationship between social media sentiments and stock returns time-varying' To provide a satisfactory response, a novel methodology—a symbiosis of Bayesian Dynamic Linear Models and Seemingly Unrelated Regressions —is introduced. Two sets of Dow Jones Industrial Average stock data and corresponding social media data from Yahoo! Finance stock message boards are used in a comprehensive empirical study. Some key findings are: (a) Affirmative response to the above question; (b) Models with only social media sentiments and market returns perform at least as well as models that include Fama-French and Momentum factors; (c) There are significant correlations between stocks, ranging from −0.8 to 0.6 in both data sets.

      PubDate: 2017-06-28T13:12:51Z
  • User Segmentation for Retention Management in Online Social Games
    • Abstract: Publication date: Available online 2 June 2017
      Source:Decision Support Systems
      Author(s): Xin Fu, Xi Chen, Yu-Tong Shi, Indranil Bose, Shun Cai
      This work proposes an innovative model for segmenting online players based on data related to their in-game behaviours to support player retention management. This kind of analysis is helpful to explore the potential reasons behind why players leave the game, analyse retention trends, design customised strategies for different player segments, and then boost the overall retention rate. In particular, a new similarity metric which is driven by players’ stickiness to the game is developed to cluster players. Three feature dimensions, namely engagement features (e.g., log-in frequency and length of log-in time), performance features (e.g., level, the number of completed tasks, coins and achievements), and social interactions features (e.g., the number of in-game friends, whether or not to join a guild, and the guild role), are employed and aggregated to derive the stickiness metric. The applicability and utility of this new segmentation model are illustrated through experiments that are conducted on a realistic MMORPG dataset. The derived results are also discussed and compared against two benchmark models. The results reveal that the new segmentation model not only achieves better clustering performance, but also improves player’s lifetime prediction by better distinguishing between loyal customers and churners. The empirical results confirm the effects of social interaction, which is usually underestimated in the current research, on player segmentation. From an operational perspective, the derived results would help game developers better understand the different retention-behaviour patterns of players, establish effective and customised tactics to retain more players, and boost product revenue.

      PubDate: 2017-06-06T07:25:17Z
  • Emotion classification of YouTube videos
    • Abstract: Publication date: Available online 26 May 2017
      Source:Decision Support Systems
      Author(s): Yen-Liang Chen, Chia-Ling Chang, Chin-Sheng Yeh
      Watching online videos is a major leisure activity among Internet users. The largest video website, YouTube, stores billions of videos on its servers. Thus, previous studies have applied automatic video categorization methods to enable users to find videos corresponding to their needs; however, emotion has not been a factor considered in these classification methods. Therefore, this study classified YouTube videos into six emotion categories (i.e., happiness, anger, disgust, fear, sadness, and surprise). Through unsupervised and supervised learning methods, this study first categorized videos according to emotion. An ensemble model was subsequently applied to integrate the classification results of both methods. The experimental results confirm that the proposed method effectively facilitates the classification of YouTube videos into suitable emotion categories.

      PubDate: 2017-05-27T07:22:22Z
  • Tour recommendations by mining photo sharing social media
    • Abstract: Publication date: Available online 19 May 2017
      Source:Decision Support Systems
      Author(s): Chih-Yuan Sun, Anthony J.T. Lee
      With the increasing popularity of photo and video sharing social networks, more and more people have shared their photos or videos with their family members and friends. Therefore, in this paper, we propose a framework for recommending top-k tours to meet user's interest and time frame by using user-generated contents in a photo sharing social network. The proposed framework contains four phases. First, we cluster geotagged locations into landmarks, and further cluster these landmarks into areas by the mean-shift clustering method. Second, we employ the Latent Dirichlet Allocation model to categorize the hashtags posted by users into landmark topics, and then use these topics to characterize landmarks and users. Third, to recommend tours for a user, we compute the tendency (or score) of the user visiting each landmark by the landmark popularity, the attraction of landmark to the user, and how many users similar to the user visit the landmark. Finally, based on the scores computed, we develop a method to recommend top-k tours with highest scores for the user. Unlike most previous methods recommending tours landmark by landmark, our framework recommends tours area by area so that users can avoid going back and forth from one area to another and save plenty of time on transportation, which in turn can visit more landmarks. The experiment results show that our proposed method outperforms the Markov-Topic method in terms of average score and precision. Our proposed framework may help users plan their trips and customize a trip for each user.

      PubDate: 2017-05-27T07:22:22Z
  • A data analytics approach to building a clinical decision support system
           for diabetic retinopathy: Developing and deploying a model ensemble
    • Abstract: Publication date: Available online 15 May 2017
      Source:Decision Support Systems
      Author(s): Saeed Piri, Dursun Delen, Tieming Liu, Hamed M. Zolbanin
      Diabetes is a common chronic disease that may lead to several complications. Diabetic retinopathy (DR), one of the most serious of these complications, is the most common cause of vision loss among diabetic patients. In this paper, we analyzed data from more than 1.4 million diabetics and developed a clinical decision support system (CDSS) for predicting DR. While the existing diagnostic approach requires access to ophthalmologists and expensive equipment, our CDSS only uses demographic and lab data to detect patients' susceptibility to retinopathy with a high accuracy. We illustrate how a combination of multiple data preparation and modeling steps helped us improve the performance of our CDSS. From the data preprocessing aspect, we aggregated the data at the patient level and incorporated comorbidity information into our models. From the modeling perspective, we built several predictive models and developed a novel “confidence margin” ensemble technique that outperformed the existing ensemble models. Our results suggest that diabetic neuropathy, creatinine serum, blood urea nitrogen, glucose serum plasma, and hematocrit are the most important variables in detecting DR. Our CDSS provides several important practical implications, including identifying the DR risk factors, facilitating the early diagnosis of DR, and solving the problem of low compliance with annual retinopathy screenings.

      PubDate: 2017-05-27T07:22:22Z
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 © 2009-2016