Elsevier

Decision Support Systems

Volume 43, Issue 3, April 2007, Pages 1044-1061
Decision Support Systems

Model-driven decision support systems: Concepts and research directions

https://doi.org/10.1016/j.dss.2005.05.030Get rights and content

Abstract

In some decision situations, quantitative models embedded in a Decision Support System (DSS) can help managers make better decisions. Model-driven DSS use algebraic, decision analytic, financial, simulation, and optimization models to provide decision support. This category of DSS is continuing to evolve, but research can resolve a variety of behavioral and technical issues that impact system performance, acceptance and adoption. This article includes a brief survey of prior research. It focuses on model-driven DSS built using decision analysis, optimization, and simulation technologies; implementation using spreadsheet and web technologies; issues associated with the user interface; and behavioral and technical research questions.

Introduction

Given the growing complexity and uncertainty in many decision situations, helping managers use quantitative models to support their decision-making and planning is an important research topic. For more than 50 years economists, psychologists, operations researchers and management scientists have investigated this topic from their various perspectives, but researchers have only just begun to understand the behavioral and technical challenges of designing, developing and implementing effective model-driven Decision Support Systems (DSS).

By definition one or more quantitative models are the dominant components that provide the primary functionality of a model-driven decision support system [65]. Also, by definition a model-driven DSS is designed so a user can manipulate model parameters to examine the sensitivity of outputs or to conduct a more ad hoc “what if?” analysis. Two characteristics differentiate a model-driven DSS from the computer support used for a decision analytic or operations research special decision study: (1) a model in a model-driven DSS is made accessible to a non-technical specialist such as a manager through an easy to use interface, and (2) a specific DSS is intended for some repeated use in the same or a similar decision situation. The general types of quantitative models used in model-driven DSS include algebraic and differential equation models, various decision analysis tools including analytical hierarchy process, decision matrix and decision tree, multi-attribute and multi-criteria models, forecasting models, network and optimization models, Monte Carlo and discrete event simulation models, and quantitative behavioral models for multi-agent simulations. Models in a model-driven DSS should provide a simplified representation of a situation that is understandable to a decision maker [9], [31], [64], [77].

Model-driven DSS are continuing to evolve, but additional research needs to be conducted. The objective of this review is to highlight recent research related to model-driven DSS and identify research needs and directions. The next section briefly summarizes an expanded framework and basic concepts associated with computerized decision support systems. Section 3 focuses on an overview of model-driven DSS issues and prior research. Also, Section 3 discusses research about model-driven DSS applications, underlying modeling techniques, delivery mechanisms, and the DSS user interface. Section 4 identifies research directions related to behavioral and technical aspects of developing, implementing and using model-driven DSS. The final section summarizes and concludes the analysis and review.

Section snippets

DSS framework and constructs

Categorizing decision support systems can assist researchers and managers in understanding how this general class of information systems impacts decision behavior and how one should design and construct such systems. The expanded DSS framework developed by Power [62], [64], [66] provides a means of differentiating decision support systems. The framework extends the terminology, definitions and concepts from prior frameworks and theory. This analysis focuses on only the model-driven DSS category

An overview of model-driven DSS research

Given that there is still some disagreement about the types of DSS and that there is a vast amount of research related to model-driven DSS, this section attempts to offer only a representative sample of prior model-driven DSS research. The intent is not to provide an exhaustive list but rather to provide an overview and analysis of model-driven DSS research. Model-driven DSS applications have been reported for all business functional areas, general management tasks, and for tasks as diverse as

Model-driven DSS research needs

Behavioral and technical research on model-driven DSS needs to address many unresolved issues associated with construction of specific quantitative models, storage and retrieval of data needed by different types of models, communication of parameters among models and other DSS components, multi-participant interaction in model use and value elicitation, and the impact of user interface design alternatives on model-driven DSS effectiveness and ease of use. Also, researchers need to investigate

Conclusions

Decision support researchers and especially those interested in using quantitative models to build model-driven DSS have an ambitious set of issues that need to be resolved. The behavioral research issues associated with building and using model-driven DSS have often been of relatively low importance because specialists and intermediaries have used the computerized complex models for decision support analyses. That approach is very limiting and costly. The technical DSS research issues are

Acknowledgements

The authors gratefully acknowledge the helpful comments on an earlier version of this paper by Ravindra Ahuja, Sean Eom, Michelle Hanna and Merrill Warkentin. We also acknowledge the helpful feedback from participants in the first SIG DSS workshop held in Seattle, WA in December 2003. Also, some of the material in this article appeared in various issues of DSS News.

Daniel J. Power is a Professor of Information Systems and Management at the College of Business Administration at the University of Northern Iowa, Cedar Falls, Iowa and the editor of DSSResources.COM, the Web-based knowledge repository about computerized systems that support decision making, the editor of PlanningSkills.COM, and the editor of DSS News, a bi-weekly e-newsletter. Dan writes the column “Ask Dan!” in DSS News.

Dr. Power's research interests include the design and development of

References (86)

  • M. Abdellaoui

    Parameter-free elicitation of utilities and probability weighting functions

    Management Science

    (2000 (Nov.))
  • R.J. Aldag et al.

    An empirical assessment of computer-assisted decision analysis

    Decision Sciences

    (1986)
  • S.L. Alter

    Decision Support Systems: Current Practice and Continuing Challenge

    (1980)
  • P.C. Bell et al.

    An experimental investigation into the efficacy of visual interactive simulation

    Management Science

    (1995)
  • I. Benbassat et al.

    Individual differences in the use of decision support aids

    Journal of Accounting Research

    (1982 (Spring))
  • P.G. Benson et al.

    Belief assessment: an underdeveloped phase of probability elicitation

    Management Science

    (1995)
  • I. Benyahia et al.

    Decision support for vehicle dispatching using genetic programming

    IEEE Transactions on Systems, Man and Cybernetics. Part A. Systems and Humans

    (1998 (May))
  • G.E.G. Beroggi et al.

    The effects of reasoning logics on real-time decision making

    IEEE Transactions on Systems, Man and Cybernetics. Part A. Systems and Humans

    (1997 (November))
  • R.H. Bonczek et al.

    Foundations of Decision Support Systems

    (1981)
  • G. Booch et al.

    The Unified Modeling Language User Guide

    (1999)
  • E.A. Boyd et al.

    Revenue management and e-commerce

    Management Science

    (2003 (October))
  • M.E. Bratman et al.

    Plans and resource-bounded practical reasoning

    Computational Intelligence

    (1988)
  • T.A. Bresnick et al.

    Airborne and space-borne reconnaissance force mixes: a decision analysis approach

    Military Operations Research

    (1997)
  • E.R. Butchers et al.

    Optimized crew scheduling at air New Zealand

    Interfaces

    (2001)
  • R.T. Clemen et al.

    The value of decision analysis at Eastman Kodak company, 1990–1999

    Interfaces

    (2001)
  • Decisioneering Staff, SunTrust Banks on Crystal Ball for Assessing the Risk of Commercial Loans, Decisioneering, Inc.,...
  • D. Delen and R. Sharda, Forecasting Box-office Receipts of Motion Pictures Using Neural Networks, Working Paper,...
  • G. DeSanctis et al.

    A foundation for the study of group decision support systems

    Management Science

    (1987)
  • F.N. de Silva et al.

    Integrating simulation modeling and GIS: spatial decision support systems for evacuation planning

    Journal of the Operational Research Society

    (2000)
  • M. d'Inverno et al.

    A formal specification of dMARS

  • D.J. Dunning et al.

    New York power authority uses decision analysis to schedule refueling of its Indian point 3 nuclear power plant

    Interfaces

    (2001)
  • S.B. Eom

    Decision Support Systems Research (1970–1999) as Cumulative Tradition and Reference Disciplines

    (2002)
  • S.B. Eom

    Decision Support Systems Research and Reference Disciplines (1970–2001): A Research Guide to the Literature and an Unobtrusive Bibliography with Citation Frequency

    (2003)
  • J.R. Evans et al.

    Introduction to Simulation and Risk Analysis

    (2002)
  • O.C. Ezechukwu and I. Maros, ORML: Optimization Reporting Markup Language, Department of Computing Technical Report...
  • R. Fourer, 2003, Software Survey: Linear Programming, OR/MS Today 30, No. 6 (December 2003) 34–35,...
  • R. Gimblett, B. Durnota and R. Itami, Spatially-explicit Autonomous Agents for Modeling Recreation Use in Complex...
  • S. Guerlain et al.

    The MPC elucidator: a case study in the design for human–automation interaction

    IEEE Transactions on Systems, Man and Cybernetics. Part A. Systems and Humans

    (2002)
  • H.B. Hayes, Decision Support Systems, Washington Technology 16, No. 13 (2001),...
  • P. Heilman, G. Davis, P. Lawrence, J.L. Hatfield and J. Huddleston, The Facilitator—An Open Source Effort to Support...
  • M. Henrion et al.

    Decision analysis and expert systems

    AI Magazine

    (1991)
  • T.J. Hess et al.

    Using autonomous software agents to create the next generation of decision support systems

    Decision Sciences

    (2000)
  • R.L. Hobbs, Using XML to Support Military Decision-making, http://idealliance.org/ (December...
  • Cited by (0)

    Daniel J. Power is a Professor of Information Systems and Management at the College of Business Administration at the University of Northern Iowa, Cedar Falls, Iowa and the editor of DSSResources.COM, the Web-based knowledge repository about computerized systems that support decision making, the editor of PlanningSkills.COM, and the editor of DSS News, a bi-weekly e-newsletter. Dan writes the column “Ask Dan!” in DSS News.

    Dr. Power's research interests include the design and development of Decision Support Systems and how DSS impact individual and organizational decision behavior.

    Since 1982, Dan Power has published more than 40 articles, book chapters and proceedings papers. His articles have appeared in leading journals including Decision Sciences, Decision Support Systems, Journal of Decision Systems, MIS Quarterly, Academy of Management Review, and Information and Management. He is also co-author of a book titled Strategic Management Skills and he authored a book on Decision Support Systems. His DSS book (2002) is a broad ranging handbook on the fundamentals of building decision support systems. His expanded DSS Framework has received widespread interest.

    Professor Power is a member of three academic journal editorial boards, the section editor of the ISWorld pages on Decision Support Systems and founding Chair of the Association for Information Systems Special Interest Group on Decision Support, Knowledge and Data Management Systems (SIG DSS).

    In 1982, Professor Power received a Ph.D. in Business Administration from the University of Wisconsin-Madison. He was on the faculty at the University of Maryland-College Park from 1982 to 1989 and received tenure as an Associate Professor in 1987. Power served as the Head of the Management Department at the University of Northern Iowa (UNI) from August 1989 to January 1996. He served as Acting Dean of the UNI College of Business Administration from January 16, 1996 to July 31, 1996. Dr. Power has been a visiting lecturer at universities in China, Denmark, Ireland, Israel, and Russia. Power has consulted with a number of organizations and in Summer 2003 he was a Visiting Faculty Research Fellow with the U.S. Air Force Research Lab Information Directorate (AFRL/IF).

    Dr. Power is a pioneer developer of computerized decision aiding and support systems. During 1975–1977, he developed a computerized system called DECAID, DECision AID. In 1981–1983, he reprogrammed and expanded the system for the Apple II PC. In 1986–1987, he designed a set of decision aiding tools for the Management Decision Assistant package from Southwestern Publishing.

    Ramesh Sharda is Regents Professor of Management Science and Information Systems and Conoco/DuPont Chair of Management of Technology at Oklahoma State University. He is the Vice Chair and Chair-elect of AIS SIG DSS. He served as Secretary/Treasurer of SIG DSS from 2002 to 2004.

    He received his B.Eng. degree from University of Udaipur, M.S. from The Ohio State University, and an MBA and Ph.D. from the University of Wisconsin-Madison. One of his major activities in the last few years was to start the MS in Telecommunications Management Program at Oklahoma State University. He has served as the founding editor of Interactive Transactions of OR/MS, an INFORMS electronic journal. He is also the computer science editor of OR/MS Today, and an associate editor of the INFORMS Journal on Computing. Ramesh has co-edited several books and is the editor for a Kluwer book series in Computer Science/Operations Research Interfaces, which has currently published 17 volumes. His research has been published in major journals in management science and information systems including Management Science, Information Systems Research, Decision Support Systems, Interfaces, INFORMS Journal on Computing, Computers and Operations Research, and many others. His research interests are in optimization applications on desktop computers, information systems support for new product development, neural networks, business uses of the Internet, and knowledge networks. His research has been sponsored by the Defense Logistics Agency, NSF, Marketing Science Institute, and several other organizations. He and his colleagues are working on using information technology to facilitate electronic commerce between the US government and small businesses. This work, sponsored by the CATT program, has resulted in development of SCORE, a tutorial for small businesses, hands on Internet training materials, and development of a web site, as well as the development of the Defense Supplier Catalog. Ramesh is also a cofounder of a company that produces virtual trade fairs, iTradeFair.com.

    View full text