Journal: JORS Article : ppl_jors_2602140
Disk used Pages: 1–15
OP: Swarna Ed: Pouly Despatch Date: 19/11/2005
r 2005 Operational Research Society Ltd. All rights reserved. 0160-5682/05 $30.00
Journal of the Operational Research Society (2005) 0, 1–15
www.palgrave-journals.com/jors
A survey of decision support system applications (1995–2001) S Eom1,3* and E Kim2,3 1
Southeast Missouri State University, Cape Girardeau, MO, USA; and 2University of Hartford, West Hartford, CT, USA To extend two previous surveys of specific decision support system (DSS) applications over the period (January 1971– December 1994), we have conducted a follow-up survey covering the period between 1995 and 2001. A total of 210 published applications are identified. To examine the development pattern of a specific DSS over time, we analysed and summarized the survey results according to (1) the area of application, (2) the year of publication in each area of application, (3) the distribution of underlying tools in DSSs, (4) a classification based on Alter’s taxonomy, and (5) the management level (operational, tactical, or strategic) for which the DSS was designed. Journal of the Operational Research Society (2005) 0, 000–000. doi:10.1057/palgrave.jors.2602140 Keywords: decision support systems; applications; survey
U
N
C
O
R
R
EC
TE
D
F
O
PR
The idea of using the computer to help decision-makers was published as early as 1963 (Bonini, 1963). It was in the early 1970s that many suggested a wide range of terms to describe the system that helps decision-makers in the process of making varying degrees of decision structures. Scott Morton (1971) is considered one of the first group of researchers who coined the term ‘decision support systems’. Since then, there has been a growing amount of research in the area of decision support systems (DSS). DSS research can be broadly categorized into application development, DSS theory building, and the study of reference disciplines. DSS applications are payoffs or fruits of DSS research activities. Therefore, it is important to periodically survey DSS applications to monitor the progress of the DSS area as a basis of setting the direction of future research. This is our third survey of DSS applications covering the period of 1995 through 2001 based on the analysis of new data in a manner that follows on, and is consistent with, the previous survey papers that covered the period of January 1971–April 1988 (Eom and Lee, 1990) and May 1988–1994 (Eom et al, 1998). We compiled a bibliography of 210 published DSS applications appearing in the literature, excluding those listed in conference proceedings and doctoral dissertations. Through this follow-up survey, our intention is to inform both academicians and practitioners about the areas in which specific DSS applications are reported as well as to provide insight about major historical trends, implications of
this study, and future directions for new theoretical developments. In addition, our intention is to compile a systematic reference for the burgeoning literature on DSS applications.
O
Introduction
*Correspondence: S Eom, Department of Accounting and MIS, MS 5815, Southeast Missouri State University, Cape Girardeau, MO 63701, USA. E-mail:
[email protected] 3 The two authors are equal contributors in this research.
Gml : Ver 6.0 Template: Ver 1.1.5
Selection criteria To compile DSS applications, we used two well-known online data sources: (1) The Global edition of ABI/INFORM, which is available on the web through ProQuests, a premier information access and retrieval system. ABI/INFORM Global database covers more than 1600 leading business and management publications, including over 350 Englishlanguage titles from outside the US; (2) Academic Search Premier database is the world’s largest scholarly, multidisciplinary full text database containing full text for more than 4650 publications, including more than 3600 peerreviewed publications in nearly every area of academic study including: computer sciences, engineering, physics, chemistry, language and linguistics, arts and literature, medical sciences, ethnic studies, and many more. The database is managed by the EBSCO information services company. For the previous survey covering the period 1988–1994, data were collected using the ABI/INFORM and INSPEC databases. INSPEC is the leading English-language bibliographic information service providing access to the world’s scientific and technical literature in physics, electrical engineering, electronics, communications, control engineering, computers, computing, information technology, manufacturing, and production and mechanical engineering. Owing to the large number of DSS articles (more than 95%) retrieved from ABI/INFORM, the impact of switching
PPL_JORS_2602140
2 Journal of the Operational Research Society Vol. ] ], No. ] ]
databases from INSPEC to Academic Search Premier seems to be negligible. To compare the trends between the two periods, the following same selection criteria used in the previous survey are used here to compile DSS applications. A DSS is defined as a computer-based interactive system that supports decision-makers rather than replaces them; utilizes data and models; solves problems with varying degrees of structure: non-structured (unstructured or ill-structured) (Bonczek et al, 1981), semistructured (Bennett, 1983, Keen and Scott Morton, 1978), semistructured and unstructured tasks (Sprague and Carlson, 1982), and structured, semistructured, and unstructured (Thierauf, 1982); and focuses on the effectiveness rather than the efficiency of decision processes (facilitating decision processes). Using the descriptor, ‘decision support systems’, a large number of articles (approximately 5400) were retrieved. To select articles that satisfy our objective, we used the following criteria. They should include:
Table 1
(1) a description of a semi- or unstructured decision; (2) a description of the human-computer interface and the nature of the computer-based support for human decision-makers’ intuitions and judgments; and (3) a description of a data-dialogue-model system.
10
A list of journals publishing DSS application articles
Rank Journals 1 2 3 4 5 6 7 8
9
Count
Interfaces Decision Support Systems European Journal of Operational Research Computers and Operations Research Journal of the Operational Research Society Computers and Industrial Engineering Decision Sciences International Journal of Production Economics Computers in Industry Information and Management InFOR Management Decision Omega International Journal of Management Science Production and Inventory Management Journal Communications of the ACM International Journal of Management International Journal of Production Research International Journal of Technology Management Journal of End User Computing Journal of Multicriteria Decision Analysis All other journals
3 2 2 2 2 2 2 26 210
O
F
Total
59 34 29 8 7 5 5 5 4 4 3 3 3
In this survey, most applications are for POM (44.16%) followed by marketing, transportation, and logistics (17.53%), MIS (13.64%), and multifunctional areas (8.44%). In the non-corporate area, usage of DSSs was widely spread out among the sectors as compared to the previous survey, which exhibited two dominant sectors of government and educational institutions. The application areas can be broadly divided into corporate functional management fields (73.33% of the total 210 applications articles) and other areas (26.67%) (Figures 1 and 2).
R
EC
TE
D
PR
Using these criteria, it is possible to narrow down the number of the articles to 210 applications for further analysis. Of these, approximately 53% of all DSSs are operational systems in use. About 43% of articles are concerned with prototype systems under various testing stages. The remaining 4% of all systems surveyed are in the conceptual design stages. Even though they are not actually developed systems, it is desirable to include those systems because they present a novel approach that may be beneficial to the development of future generations of DSSs. Table 1 shows a list of journals publishing DSS application papers.
O
Classification by application areas
R
Analysis
U
N
C
O
To examine the development pattern of a specific DSS over time, we analysed and summarized the survey results according to (1) the area of application, (2) the year of publication in each area of application, (3) the distribution of underlying tools in DSSs, (4) a classification based on Alter’s taxonomy, and (5) the management level (operational, tactical, or strategic) for which the DSS was designed. It should be noted that the published DSS applications are not a random sample of DSS applications in practice. Many DSS applications go unreported. Therefore, we should not interpret the results of this survey as if they reflect real world practice.
Corporate functional management area There are 154 applications in the corporate functional management area. Of the corporate functional management applications, production and operations management (POM) contains the largest number of application articles published (44.16%), followed by marketing, transportation, and logistics (17.53%), management information systems (13.64%), multifunctional systems (8.44%), finance (6.49%), strategic management (3.9%), and human resources (3.9%). In this survey, systems for accounting and international business are not found. The POM application (68 applications) has been the predominant DSS application area over the past decade. Production/operations management process has several distinctive components, from planning for aggregate de-
Q1
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 3
a
Inter-Org. decisions 2% Strategic Mgmt. 4% Human Resources 4%
Other Areas 26.7% 56
Finance 6% Multi-Functional Application 8% MIS 14%
Corporate Functional 73.3% 154
Marketing/Transportation 18%
Production/Operation 44%
Agriculture 7% Urban/ Comm Plg 7% Military 11%
b Corporate Functional 73.3% 154
Natural Resources 13% Hospital/HealthCare 13%
Other Areas 26.7% 56
Misc. 14% Education 16% Government 20%
EC
Year
TE
1995-2001
1988-1994
50
100 Number of articles
R
0
150
200
C
O
R
Figure 2 The proportions of DSS papers concerning operational, tactical, and strategic decisions changed during 1988– 2001.
N
mand and product planning, capacity/product planning (fixed and adjustable), master scheduling, operations design, scheduling and controlling, inventory management, resource management, and others. A focus on the customer is the cornerstone of modern management philosophy. Managing aggregate customer demand triggers the operations management process. The second survey reported several applications for aggregate demand or item demand forecasting.
U
This survey finds only one application to support demand management of a public power corporation when estimating energy demand (Mitropoulos et al, 1995). Product planning is another dimension of advance planning. To cope with the changing customer tastes, many DSS are developed to support product design and development (Matsatsinis, 1995; Chau and Bell, 1996) and to support product planning research and development (Badri et al, 1997). To meet aggregate demand, capacity must be planned as part of long-range planning. Fixed capacity planning involves establishing and adjusting levels of capacity needs of key resources such as manpower, machinery, etc. DSS is developed to optimize capacity planning (Bermon and Hood, 1999) and flexible manufacturing systems design (Borenstein, 1998). Fixed capacity planning enhances human potential through the use of process technology such as computer-aided design (Wierzbicki and Granat, 1999) and numerical control equipment design (Monplaisir et al, 1997). The most important DSS applications in this area are longterm production planning and control systems (Bowers and Agarwal, 1995; Carravilla and de Sousa, 1995; Tsubone et al, 1995; O¨zdamar and Birbil, 1999; Buehlmann et al, 2000; Pfeil et al, 2000; Katok et al, 2001b), and medium-term master scheduling of specifying production by item, by period, and by capacity group (Belz and Mertens, 1996; Bistline et al, 1998, Degraeve and Schrage, 1998, Huang et al, 1998). Master scheduling can only be managed effectively with careful planning of inventory planning and
PR
D
Operational Level Decisions Tactical Level Decisions Functional Level Strategic Decisions Business Level Strategic Decisions Corporate Level Strategic Decisions for Domestic Co. Corporate Level Strategic Decisions for Multinational Co.
O
O
F
Figure 1 (a) All articles are broadly divided into corporate functional management (154) and non-corporate areas (56). Corporate functional management accounts for 73% of the application articles and is further divided into eight functional areas. (b) Twentyseven percent of the application papers concern non-corporate subjects; this is subdivided into eight areas.
PPL_JORS_2602140
4 Journal of the Operational Research Society Vol. ] ], No. ] ]
O
O
F
Wierenga and Van Bruggen, 2001), price, place (distribution), and promotion strategy. Among the subareas of marketing applications, distribution strategy has the most number of applications (12 out of 27) that include distribution network design, pipeline route selection, selection between private and common carriers for delivery, transportation demand forecasting (Fierbinteanu, 1999), and vehicle routing (Bausch et al, 1995; Huntley et al, 1995; Basnet et al, 1996; Adenso-Dı´ az et al, 1998). In developing promotion strategy, DSS are developed to find the most profitable mail stream for each customer, planning the pricing and sales effort policy of the sales force, and promotion evaluation, tracking and planning (Davis and Sundaram, 1995). Another major DSS application area is MIS domain, which has 21 applications. Ninety percent (18) of these applications are in the following areas—negotiation support systems, DSS generators, GDSS shell (Csa´ki et al, 1995), and data communication network design. Some minor applications include agent-enabled DSS design (Hess et al, 2000), information system project portfolio planning, and business process optimization. One worthy finding during the survey period is the emergence of negotiation support systems as a major DSS application. NSS are developed to support group negotiation (Espinasse et al, 1997; Rangaswamy and Shell, 1997), negotiation activity analysis (Kersten and Noronha, 1999), and crisis management. Various types of DSS generators are developed to generate alternatives (Fazlollahi and Vahidov, 2001), web-based DSS generators (Mustajoki and Ha¨ma¨la¨inen, 2000), analyzing preference desegregation, and multicriteria trade-off decisions with imprecise specifications. It is worth mentioning that several web-based DSSs have been developed (Rangaswamy and Shell, 1997; Kersten and Noronha, 1999; Mustajoki and Ha¨ma¨la¨inen, 2000). Many DSS are developed to effectively design fibre-optic networks (Cosares et al, 1995), to plan cost-effective synchronous digital hierarchy network architecture (Shyur and Wen, 2001), to plan inter-office facilities networks, and to plan regional telecommunication networks. The majority of DSS applications in the finance area are developed to support credit evaluation and management (Curnow et al, 1997), selection of financial audit portfolios and project portfolios, management of fixed income portfolios, credit risk management of home mortgage portfolios, and to optimize investment policy and strategy (Palma-dos-Reis and Zahedi, 1999). In the human resources management area, DSS are developed to help the user select human resources, assign jobs, plan training courses and select health insurance options (Nussbaum et al, 1999). In the strategic management area, six applications are found in this survey. They are strategic logistics planning, strategic planning for Clean Air Act compliance, strategic alternative evaluation (Tavana and Banerjee, 1995), manufacturing strategic planning (Price et al, 1998), and locating foreign manufacturing plant.
U
N
C
O
R
R
EC
TE
D
PR
control (Chaudhry et al, 1996, Chen and Sinha, 1996, Katok et al, 2001a). Master scheduling must be executed through the operations scheduling and control of continuous and repetitive operations such as airline crew scheduling (Jarrah and Diamond, 1997; Dillon and Kontogiorgis, 1999; Butchers et al, 2001), gasoline blending (Rigby et al, 1995), and airline operations control (Mathaisel, 1996). DSS also support large-scale operations such as managing large-scale projects (Ju¨ngen and Kowalcyk, 1995; LeBlanc et al, 2000; Dey, 2001). DSSs also helped manage operating resources such as daily allocations of the automated, guided vehicle in automobile plants (McHaney and Douglas, 1997), adjusting maintenance float system availability levels (Madu et al, 1995), etc. A systematic table of classification by application areas and corresponding reference numbers in the bibliography can be found at: http://cstl-hcb.semo.edu/eom/research/ a_survey_of_decision_support_sys.htm. The success of most industries often hinges on the accuracy of their forecast of demand. In this regard, DSSs are developed to support electrical demand pattern analysis, cycle time reduction, and the inventory-order-quantity and pricing decisions (Kobbacy et al, 1995; Chaudhry et al, 1996; Chen and Sinha, 1996; Mantrala and Rao, 2001). The marketing, transportation, and logistics area is the second largest (27 out of 154) application area in corporate functional management. The core of marketing can be described as the process of planning and executing four controllable variables (marketing mix) of product, price, promotion, and place to satisfy customer needs. The elements of marketing mix are managed as a cohesive marketing programme. The marketing programme is the result of strategic marketing process. This process consists of situation analysis of SWOT (organization’s internal Strengths and Weaknesses, and its external Opportunities and Threats), followed by the goal setting phase which specifies which customers to target (who) and which customer needs to be satisfied (what). DSS applications compiled in this survey have been shown to be indispensable tools in every step of the strategic marketing management process. As discussed, the planning phase of the strategic marketing process of identifying SWOT is a complex process. A hybrid intelligent DSS is developed to support the development of marketing strategy (Li, 2000). Based on the SWOT analysis, an organization needs to find the market segment (Levin et al, 1995) on which it will focus its efforts as a prior step to developing marketing programmes. Market segmentation requires marketing research into product trends and pattern analysis (Jiang et al, 1998) and judgmental forecasting on market demand (Lim and O’Connor, 1996). With the selected market segment, marketing managers now know which customers to concentrate on and which customer needs must be satisfied. The next step is to develop a marketing mix strategy of deciding product (Dutta et al, 1997; Ozer, 1999;
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 5
Other areas
U
N
C
O
R
R
EC
TE
D
F
O
PR
Non-corporate areas have 56 applications. Among these, government appears to have the most DSS applications (19.64%), followed by education (16.07%), miscellaneous (14.29%), natural resources (12.5%), hospital and healthcare (12.50%), military (10.71%), urban/community planning and administration (7.14%), and agriculture (7.14%). Almost 20% of all applications (11 out of 56) are in the government sector. These applications are distributed among data-processing acquisitions (Barba-Romero, 2001), online crisis management (Mak et al, 1999), managing the DOE hazardous waste cleanup programme, US bridge networks improvement, medium-term economic planning, China’s coal and electricity planning, railway infrastructure scenarios development, and random sampling-based testing of urine specimens instead of testing all collected specimens (Chari et al, 1998). In the education area, DSSs are used in course scheduling, examination composition planning, proctor assignment, university timetabling (Foulds and Johnson, 2000; Dimopoulou and Miliotis, 2001), and enrollment projections and locating a new school (Taylor et al, 1999). In the health-care industry, DSSs are developed to improve hospital decisionmaking processes, from patient admission to discharge and billing, which permits an interactive, multidirectional sharing of information and knowledge among nurses, physicians, and administrators (Forgionne and Kohli, 1996), to help collaborative medical decision-making, schedule home-
health-care nurses, improve hospital material management process (Ramani, 2001), control sexually transmitted diseases, and track key indicators of mental health providers’ productivity (Mohan et al, 1998). In the area of natural resources, DSSs have been developed to manage a forest ecosystem (Church et al, 2000), to manage lake reservoir and micro-watershed (Datta, 1995), and for environmental planning (Splettstoesser and Splettstoesser, 1998), and water strategic planning. Military applications are developed in managing army housing (Forgionne, 1997), managing Coast Guard buoy tender operations, determining the size and shape of the South African national defence force (Gryffenberg et al, 1997), and facilitating the privatization of military housing (Forgionne, 2001). Urban and community planning DSSs are applied to plan emergency evacuation, snow removal and disposal (Campbell et al, 2001), plan urban transportation (U¨lengin et al, 2001), and manage urban waste. In the area of agriculture, DSS are developed in planning agri-environmental activity, assessing farm-animal welfare, allocating resources for crop protection and biotechnology R&D projects (Sonntag and Grossman, 1999), and managing feed distribution at a cattle ranch (Tracey and Dror, 1997). Miscellaneous applications include assessing decision technology system journal quality, optimizing the location of a new ice-hockey arena, planning large and multievent elimination tournament (Kostuk, 1997), locating installations for industrial waste management, speeding up the process of crystal growth for protein, and competitive pricing for law firms (Tavana et al, 1998), etc.
O
Multifunctional management DSS (Organizational DSS) are increasingly developed and deployed in the following: production and distribution planning, production-planning and delivery-quotation systems, multifunctional decision support for a jewellery manufacturer, strategic and operational management with optimization, aircraft routing with crew planning and work assignment, optimization of production, inventory, and distribution, and yield management with pricing and fleet planning in the car rental industry. Yield management in the car rental industry integrates the four major strategic decisions: planning fleet levels, deploying the fleet, managing revenue (yield), and deciding the optimal mix of services. In doing so, Hertz designed the yield management DSS that integrates four other DSS for fleet planning, for daily planning and distribution, for product offering, and for cost allocation. The last area of DSS application is the area of interorganizational decisions such as supply chain planning (Koutsoukis et al, 2000), collaborative planning and forecasting (Raghunathan, 1999), and designing interorganizational DSS (Lin et al, 2000). Although these applications may represent a small proportion of all DSS in the survey, this development of inter-organizational DSSs is a notable development that needs to be discussed further later.
Distribution of entries by classification and year of publication As shown in Table 2 and Figure 3, approximately 30 applications were published annually to make a total of 210 DSS applications during the period 1995–2001. This is a decrease compared to our previous survey (May 1988–1994) that reported approximately 48 applications annually. But it is still much more than the first survey (1971–1988) that had approximately 12 annual applications. The dominant application area of DSS is still production and operations, followed by marketing and logistics, and management information systems field. The other corporate functional areas remain steady except accounting and international business. Those areas were not explored in this time period. A notable change in the non-corporate areas is that applications are spread out to most areas—government, education, miscellaneous, healthcare, natural resources, and military in this survey. In the previous survey (Eom et al, 1998), approximately 60% of applications are in government and educational institutions while in this survey, they represent 33%.
PPL_JORS_2602140
6 Journal of the Operational Research Society Vol. ] ], No. ] ]
Table 2
Distribution of entries by application areas and years of publication
Area
1995
Corporate functional area Finance Human resources Management Information Systems Marketing/transportation Production/operation Strategic management Multifunctional application Inter-organizational
1 4 4 13 3 2
Non-corporate area Agriculture Education Government Hospital/healthcare Miscellaneous Military Natural resource Urban/community planning
1996
1997
1998
1999
2000
4 3 1 5 15
2
2
1
3 5 7
2
1
1 2 4 4 9 1 3 1
1 1 1 1 1 3 1
2 2 1 1
1 1 1 34
32
27
5 3 8 2 2
1 1 2
1 1 2 3
30
154 11 6 21 27 68 6 13 3
2 1
2
56 3 9 11 6 8 6 7 4
30
29
210
1 1 4 1 2 2
3 1 1
3 1 28
4 2 7 1 2
Total
O
F
Yearly total
4 9 1 1
2001
O
40
Table 3
Distribution of tools First
Second
This one
Deterministic model Linear programming Goal programming Transportation model Network model Inventory model Integer programming Nonlinear programming Dynamic programming
85 18 9 6 15 8 19 6 4
132 28 5 18 23 7 32 11 8
99 27 4 1 17 3 34 6 7
Stochastic model Queuing model Markov process model Simulation models Decision trees/Game theory Other stochastic models
58 3 6 41 9
57 1 4 41 11 3
41 2 3 28 8
Forecasting and statistical models
40
47
39
Others Other MCDM Models MADM MOLP AHP Nonlinear goal programming Spreadsheet modelling Graphics Artificial intelligence Visual interactive modelling Query language or 4GL Others
104 11 5 5 1 0 24 46 12 0 0 0
345 67 43 10 12 2 22 81 73 40 21 41
328 28 10 1 16 1 8 18 96 46 23 109
PR
30 25 20 15 10 5 0 1996
1998 Year
1999
2000
2001
Distribution of papers by year.
EC
Figure 3
1997
TE
1995
D
Number of papers
35
R
Distribution of underlying tools in DSS
U
N
C
O
R
Management science/operations research (MS/OR) models have been essential elements of DSS tools as Table 3 indicates. As shown in the previous surveys, forecasting and statistical models, integer programming, simulation, linear programming, and network models have been powerful MS/ OR tools that have been increasingly embedded in the model base of DSSs (Table 3). There are several notable changes in the distribution of tools in this survey. Firstly, MS/OR models are still essential elements of many DSSs. However, this survey clearly shows that other models and tools have been increasingly embedded in the DSSs, including visual interactive modelling, artificial intelligence tools such as AI languages, rules, knowledge base, voice recognition, neural networks, and heuristics. There is a clear
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 7
O
O
F
in the solution algorithms in 1990s were in the area of mixed integer programming (Shim et al, 2002). Thirdly, other recent developments in this area include the family of artificial intelligence methods. That is the single most widely embedded tool in DSSs in this survey. About 24% (50 out of 210 total applications) embedded some form of artificial intelligence tools. It confirms the previous survey prediction of the increased importance and use of expert DSSs (Eom et al, 1998). Many new tools are increasingly being added in the development of DSSs in organizations. In addition to MS/ OR models as identified in this survey, these emerging tools include the Geographic Information Systems (GIS), objectoriented methodologies (modelling, programming and database), intelligent agents, World Wide Web technologies, and other internet technologies. Artificial intelligence tools had more applications (approximately 19% of total tools used) in DSSs than any other tools in this study. Among the AI tools, rules are most widely used followed by heuristics, knowledge base, fuzzy sets, agents, genetic algorithms and others. In this survey, many DSS developers integrate commercial solvers into DSSs to generate optimum solutions. Those are, for example, CPLEX (LP solver and mixed IP solver), LP-88 (Eastern Software’s LP solver), Microsoft Excel Premium Solver Plus and others.
Classification based on Alter’s taxonomy
U
N
C
O
R
R
EC
TE
D
PR
observable trend in the DSS model area that two non-MS/ OR tools are becoming powerful DSS tools: artificial intelligence, and visual interactive modelling. Artificial intelligence already appeared more often than any other MS/OR model in the last survey and it has continued to be the tool most frequently embedded in DSS, more often than all other MS/OR models. Carlsson and Turban (2002) also mentioned that AI tools are emerging in DSS design and development to make DSS more intelligent. Visual interactive modelling is the second most widely used DSS tool and permits a decision-maker to generate and modify various visual representations of decision alternatives. Many commercial software packages now include visual interactive sensitivity analysis capabilities. Other emerging tools embedded in DSSs are AHP or methods for outranking relations such as ELECTRE and PROMETHEE. The ELECTRE method was first introduced in 1968 for outranking relations for modelling the decision-maker’s preferences in multicriteria decision-making (MCDM) problems. Compared to this, AHP is based on multiple attribute utility theory (MAUT) that represents preferences by means of utility function. These methods are different in multicriteria aggregation procedure. PROMETHEE defines global ranking, which means that it provides the decisionmaker with a ranking of all potential actions. ELECTREE methods incorporate some criteria as rejection points that block the outranking relationship between two potential actions. Owing to these differences, in this survey, PROMETHEE methods were more widely used in group decision-making or MCDM. Detailed comparison of AHP, ELECTREE, PROMETHEE, and preference desegregation methods (ie UTA) can be found in Zopounidis and Doumpos (2002) who applied these techniques to financial decision-making domain. Secondly, use of deterministic models and stochastic models in DSSs are proportionally decreasing (see Table 3) while other models in DSSs are increasing. Our earlier surveys reported that linear programming and integer programming are MS/OR tools that are frequently embedded in DSSs. The current survey reconfirms our earlier observations of the frequent use of linear programming and integer programming in mathematical programming systems. As observed by Nemhauser (1993), integer programming has assumed a much more important role in supporting decisions such as scheduling flexible manufacturing systems, assigning manpower, and scheduling course and instructor, planning computer capacity, media allocation, fleet mix, designing freight/distribution networks, and so on. Nemhauser (1993) points out that due to new advances in algorithms such as the new interior point, branch-and-bound algorithms and simplex methods as well as computer technology and advanced implementations of optimization algorithms that have been incorporated in commercially inexpensive software, it is possible for unsophisticated users to obtain readily understandable outputs. The biggest gains
Alter (1980) suggested a classification scheme, based on the ‘degree of action implication of system outputs’ (that is, the degree to which the system’s output could directly determine the decision). In this survey, none of the 210 published DSS applications belong to file drawer systems, or data analysis systems. File drawer systems allow on-line access only to particular data items while data analysis systems support online data retrieval, manipulation, and display of current and historical data by means of such operations as pictorial representation, summarization, and calculation of data. Care must be exercised when interpreting the result of this survey. The nature of published DSS applications is very much different from that of implemented DSS applications. If a DSS that is currently used retrieves data item based on a well-established method, it is not probably published. About 4% of all applications (nine articles) represent analysis information systems, which are capable of manipulating the internal data from transaction processing systems and augmenting the internal data with external data using statistical packages and other small models to generate management information. The next type of system, accounting models, comprises approximately 1% of the total applications (two articles). Accounting systems facilitate planning by calculating the consequences of planned actions on the estimate-of-income statements, balance sheets, and other financial statements. Accounting models are based on
PPL_JORS_2602140
8 Journal of the Operational Research Society Vol. ] ], No. ] ]
Table 4
Classification based on Alter’s taxonomy Number of proportion articles
Survey of 1971–April 1988 13 57 81 14 23 15 0 203
27 104 68 7 47 18 0 271
D
TE
EC
R
R
O
C
Classification by the level of management
N
We conduct further analysis to examine the management level (operational, tactical, or strategic) for which DSS are developed. Figure 2 shows the number of specific DSS applications and their composition among operational, tactical, and three levels of strategic decisions for different periods from 1988 to 2001. Figure 2 shows that the DSS applications to strategic level decisions (functional-level strategic decisions and business-level strategic decisions) are increasing while operational level DSSs are declining. In
Survey of 1995–2001 48 107 45 2 8 0 0
23% 51% 21% 1% 4% 0% 0%
210
the previous survey (Eom et al, 1998), operational level DSS articles published in 1988–1994 were 105 (67%) while 85 (53%) in this survey period (1995–2001). In these two surveys, tactical-level strategic decisions increased from 29 (18%) to 43 (27%) and business-level strategic decisions rose from 13 (8%) to 21 (13%). The other strategic decision areas remain steady. In other words, in the previous survey period (1988–1994), 85.5% of the published DSS applications were concerned with operational or tactical decisions while in this survey it is 80.5%. This survey shows that approximately 20% of the DSS applications (31 articles) are developed to support strategic decisions and 80% are developed for tactical or operational levels of decisions. Still, the majority of DSSs are being applied to support operational and tactical decisions. This result shows that DSS research has focused more on the strategic problems from the middle of the 1990 s. This trend may be continued in the foreseeable future. Even though the topic of supporting strategic decisions is appearing more often in DSS application development research, it should be the focus of even more DSS research. The nature of strategic decisions is also changing significantly from single organization’s strategies to those of extended enterprises and virtual corporations. The DSS tools we have utilized to support strategic planning of a single organization are not good enough to support strategic decisions of the extended enterprise systems. Strategic decision support encompasses a wide range of different strategies such as functional strategy, business strategy, and global corporate strategy. Rapid advancement in telecommunications technologies triggered a revolution in the structure and operations of many firms in the internetdriven global economy. Consequently, we are witnessing the growing importance of new types of organizations—virtual corporations, extended enterprises, and trans-enterprise systems. DSS researchers responded to the changing organizational environment and inter-organizational DSSs is an important on-going research topic to effectively support the changing nature of decisions faced by extended enterprise and virtual organizations (Eom, 2004).
PR
definitional relationships and formulas, unlike other types of MS/OR models. Twenty-one percent of all applications (45 articles) utilize representational models to estimate the future consequences of actions on the basis of partially nondefinitional models, including all simulation models. Fiftyone percent of all applications (108 articles) are classified as optimization models that generate the optimal solutions consistent with a series of constraints. Finally, 23% of all applications (48 articles) are categorized as suggestion models which lead to a specific suggested decision for a fairly structured task. Such systems perform mechanical calculations and leave little room for managerial judgment. We find that three model types dominate: optimization (51%), suggestion (23%), and representation (21%) models. When compared to our previous survey of 1998, we are witnessing the continued importance of optimization systems and suggestion models that lead to a specific suggested decision. There is a definite proportional increase of optimization and suggestion models and a decrease in the number of representation models embedded in DSSs, as shown in Table 4. It appears that applications of optimization models are increasingly dependent upon DSS front ends to make them more easily accessible to end users (decisionmakers). We conducted further analysis to examine the management levels (operational, tactical, or strategic) for which DSSs are designed.
U
10% 38% 25% 3% 17% 7% 0%
F
Total
6% 28% 40% 7% 11% 7% 0%
O
Suggestion model Optimization model Representation model Accounting model Analysis information systems Data analysis systems File drawer systems
Survey of May 1988–1994
O
Alter’s taxonomy
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 9
Negotiation support systems (NSS)
N
C
O
R
R
EC
TE
D
This survey clearly indicates that NSS are being developed to support various negotiations. Lim and Benbasat (1992– 1993) presented a traditional view of negotiation support systems. This view is based on the desktop computer-based DSSs with communication links between negotiators. A NSS is a system of the individual DSSs assigned to individual bargainers and electronic communication systems that permit both computer-mediated and non-computermediated communication between bargainers. NSS should support the decision-making process in any negotiation situation of interdependence, perceived conflict, opportunistic interaction, and possibility of agreement. A theoretical model proposed seeks to improve negotiation outcomes in terms of the following five dependent variables—time to settlement, satisfaction, distance from efficient frontiers, distance from Nash solution (fairer solution), and confidence with solution. Using traditional architecture, a specific NSS is developed to deal with a hostage crisis situation (Wilkenfeld et al, 1995). Espinasse et al (1997) developed a prototype negotiation support system, NegocIAD, based on a multicriteria conceptual framework of the negotiation based on a multiagent architecture from distributed artificial intelligence.
U
F
O
Knowledge-based decision support systems As shown in Table 4, many DSSs in this survey are increasingly incorporating knowledge of domain, modelling, and analysis into systems to provide users the capability of intelligent assistance. Often, computations are performed using different types of math models to generate solutions while expert system components in the system provide necessary data, monitoring the calculation process, and evaluating math model results to assist users on a real time basis. Hence, these types of systems are more effective if a decision problem has a high level of uncertainty or requires data and knowledge intensively. For example, Belz and Mertens (1996) developed a system that included three different types of expert knowledge modules to assist at different phases in handling production disturbances. As discussed in the previous article (Eom et al, 1998), the use of intelligent agent is increasing in DSS development and usage as shown in Table 3. The primary purpose of agent research is to ‘develop software systems which engage and help all types of end users’ in order to reduce work and information overload, teach, learn, and perform tasks for the user (Riecken, 1994). Intelligent agent technology is widely applied in many different domains including expert systems, DSSs, cognitive science, psychology, databases, e-commerce, and others. Wang et al (2002) proposed intelligent negotiation agents to support the current organization’s decisions that are more pluralistic and less hierarchical and determined by the argumentative and evidential value. Commercial products such as DSS Agent from Microstrategy work as a
PR
The third survey of DSS applications reconfirmed the earlier observations we made in the second survey (Eom et al, 1998). The second survey highlighted the importance of the business intelligence system which comprised of data warehousing and an analytical environment (data mining, online analytical processing, etc.); a host of DSS tools (AI tools and the internet and web-based technologies) appeared during the survey. These technologies have influenced significantly and continue to influence the development of decision support systems. The third survey reveals several important changes in DSS application development including the development of negotiation support systems, organizational decision support systems (ODSS), inter-organizational DSSs, intelligent DSS, and web-based DSS. It may not be possible to detect the changing nature of decision support and DSSs without considering several changes in the contemporary business environment such as increasing globalization of business, transformation of industrial economies to knowledge- and information-based economies, transformation of the enterprise, and emergence of the digital firm (Laudon and Laudon, 2004). Especially, the emerging economies and digital firms have a profound impact on the DSSs area as well as the entire information systems area. The essence of the digital economies and digital firms is that the relationships with business partners are digitally enabled and mediated through digital networks.
Later Kersten and Noronha (1999) presented a web-based asynchronous NSS generator/shell, INSPIRE-INterneg Support Program for Intercultural Research. The traditional NSS architecture of Lim and Benbasat has been expanded by WWW-based negotiation support systems architecture. The web-based architecture is based on the net-centric computing paradigm and object-oriented design. The client/ server model architecture allows the user with only a web browser and an internet connection to be part of NSS. Programs such as electronic bargaining facilities, analytical tools, quantitative and qualitative tools reside at their developers’ home site and when the user needs a part of functionality, it will be downloaded. The NSS system shell supports most negotiation activities such as preference assessment, analysis of alternative offers, counter-offer evaluation, etc. Bui et al (2001) developed a prototype NSS to show how these multiple attributes can be captured to augment standard negotiation processes in order to support electronic market transactions. Using a combination of utility theory and MCDM, they proposed heuristic algorithms and incorporated market-signalling mechanisms. This not only allows for the systematic evolution of negotiation positions but also improves both market transparency and efficiency.
O
Implications and suggestions for future DSS applications research
PPL_JORS_2602140
10 Journal of the Operational Research Society Vol. ] ], No. ] ]
web-based optimization DSS implemented by BASF, the world’s leading chemical company, exhibits several advantages of the Web-based optimization DSS over the traditional optimization tools implemented on separate user’s computers (Lee and Chen, 2002) due to the fact that optimization engines are stored on the server and the results of optimizations are also stored on the server. It is easy to access the optimization system by any web browser anywhere, anytime. It is easy to deploy and maintain optimization tools that can be easily integrated with other enterprise system applications such as data warehouse and enterprise resources planning via web-based standard interfaces. Optimization results are easy to communicate among multiple users in an organization such as functional managers, management scientists, top management, etc.
Organizational (multifunctional) DSS
O
O
F
During the 1990s, the focus of DSS research shifted from the optimization of functional decisions in an organizational unit to the optimization of an organizational decision that affects several organizational units. The best example of ODSS is enterprise resources management (ERM) systems/ enterprise resource planning (ERP) systems. ERP systems integrate and optimize the entire organization’s multiple functional units (marketing, human resources, production, etc.). The ERP systems support multiplant, multilocation global corporations operating world-wide. The essence of ERP systems is the ability of tightly integrating the various functional units of an organization using a systems/process view of the organization. While production planning DSS in the 1970s could not produce production planning that simultaneously considered its impact on the other functional areas of the organization, ERP systems produce production planning that results in organization-wide optimization with the capability of analysing the overall impact on the organization (Eom, 2002a, b). This survey shows that an increasing number of multifunctional DSS has been implemented in various industries such as airlines (Rakshit et al, 1996; Desrosiers et al, 2000), telecommunications (Kim et al, 1997), car-rental (Carroll and Grimes, 1995) and fast food (Heuter and Swart, 1998) to improve and optimize production, inventory, and distribution (Leachman et al, 1996; Lee and Lee, 1999; Murthy et al, 1999; Brown et al, 2001; Mallya et al, 2001).
R
EC
TE
D
PR
front-end for relational database management systems (RDBMS). It enables users to navigate the data warehouse, report generation based on schedule, and to receive database alerts and updates. But this one lacks learning or advising capability that is the most important feature of being an agent. Another commercial product, Apple Data Detectors is an intelligent agent that extracts semantic data from everyday documents of users without much user help using the knowledge base. It is unobtrusive, being able to support user needs, and works in a collaborative manner (Nardi et al, 1998). One important purpose of intelligent agent technology embedded in DSS is to access and to collect necessary information over the internet. To facilitate this activity, RETSINA architecture was introduced (Sycara et al, 1996). RETSINA architecture is based on the distributed multiagents collaboration to locate information source, to access, filter, and integrate information to support decision-making. Mobile agent will be utilized to make DSSs more effective in collaborating among users. Mobile agent application to ecommerce was well introduced in Wagner and Turban (2002). They claimed that despite the limitations and risks, mobile Web agents have been hailed as one of the most attractive technologies for the near future and are considered by many an absolute necessity for e-business in light of the exponential information load increase for buyers and suppliers (Wagner and Turban, 2002). This multilocation information processing capability of mobile agents will help collaborative decision-making activities be more effective and efficient. The use of intelligent agents will be more extensive than ‘stimulus agents’ suggested in active DSS as introduced by the 1992 Franz Edelman DSS prize-winning paper (Angehrn, 1993). Stimulus agents will act as experts, servants, or mentors to decide when and how to provide advice and criticism to the user, while the user formulates and inquires about its problems under the continuous stimulus of electronic agents. The user is expected to use multiagents including stimulus agents in a collaborative manner to fully utilize the capability of mobile agents and the Web technology.
R
Web-based decision support system
U
N
C
O
The WWW enabled us to build a corporate intranet that facilitates user access, and analyses and distributes timely business information from corporate databases through OLAP. The internet and corporate intranets opened the possibility of building DSSs to deal with problems of a multilocation nature. The Web is basically client/server computing the services of which are implemented on a server and offered by that server to clients. Hence, three ingredients of computing—processing, resources, and know-how—are located on the server and clients download them when they are needed. The integration of optimization engines and the internet allows any users on intranet and extranet to execute an optimization model anytime and anywhere. The case of a
Inter-organizational decision support systems (IODSS) As noted by Lambert and Cooper (2000, p. 65), ‘One of the most significant paradigm shifts of modern business management is that individual businesses no longer compete as solely autonomous entities, but rather as supply chains.’ To exploit the challenges and opportunities created by the paradigm shift, inter-organizational DSS has emerged as a strategic tool for achieving competitive advantages in the
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 11
O
O
F
forecasting DSS as well as to K-mart’s forecasting systems. These links allow both K-mart and Wal-Mart to order and automatically replenish several product items from WarnerLambert. ERP systems of companies in an extended supply chain are interlinked, and the collaborative planning layer (subsystem) is integrated as an essential part of IODSS. The third survey is conducted to monitor the progress of the DSS applications development area as a basis of setting a future research direction. A series of DSS application surveys we have conducted covering 1970–2001 tells us that DSS helped organizations increase profits, on-time delivery rates, and annual throughput, and that DSS decrease inventories, the cycle times, and costs, etc. The most distinguishable and noteworthy differences in this survey from the previous surveys, among others, are the emergence of ODSS and inter-organizational DSSs. These noteworthy developments did not happen by accident. Rather, they are the fruits of the combined and sustained efforts of the researchers in the DSS and reference disciplines, practitioners, and information technology vendors who provide all the infrastructures and tools. The raison d’tre of the DSS field is to develop DSSs that improve personal, departmental, organizational, and interorganizational decision-making. The core of DSS discipline is application development. Its worthiness depends on the quality of DSSs we develop in terms of financial and nonfinancial benefits to the organizations. This survey shows that more than 30 years of continued efforts of researchers and practitioners have resulted in the development of the inter-organizational DSS, a new frontier in DSS, evolved from single-user DSS. The complexity of DSS development increases as the focus of supporting entities shifts from individual to group, organization and multiorganizations. Often, it may be necessary to take an evolutionary approach. Inter-organizational DSS may be built on organizational DSS, which, in turn, can be built on the group support systems and single-user DSS. Above all, organizational DSS and inter-organizational DSS must be built on core information technology infrastructure. Over the past decade, many firms invested in their core information technology infrastructures including the business intelligence system. The infrastructure includes data warehousing, business intelligence software tools, pre-packaged analytical applications, and telecommunications and internet technologies. For an example, Oracle is the market leader in business intelligence products. The core of its business solutions is Oracle 10 G relational database management systems with embedded online analytical processing and data mining, along with Oracle business intelligence warehouse builder and Oracle enterprise planning and budgeting tools (Vesset and Morris, 2004). Oracle 10 G is based on the Grid computing technologies that connect a group of low-cost servers connected by Oracle software, rather than mainframe computers. Nevertheless, the Oracle Grid runs applications faster than the fastest
U
N
C
O
R
R
EC
TE
D
PR
global marketplace. Inter-organizational DSS is a DSS that is primarily built on the extranets which can be executed over the Web to provide information, communication, and decision support (modelling and analysis) tools in order to create and sustain the competitive advantages of all consortium members of industrial networks. The critical element of IODSS is an integrated decision support modelling and analysis tool to handle the uncertainties in estimating demand, sales, lead time, supplier reliabilities, etc. Industrial networks (extended enterprise or integrated industry-wide systems) electronically link multiple organizations in the same industry vertically (manufacturers, suppliers, and suppliers’ suppliers). It is also possible to link horizontally (linking competing firms in an industry). Extended supply chain management is the best example of inter-organizational DSS applications. The supply chain is a series of physical entities associated in the entire process beginning with procurement of raw materials through several multiple-tier suppliers (upstream supply chain), and internal manufacturing processes used by an organization (internal supply chain), and ending with the delivery of the finished goods to the customers, distributors of finished products, and retail outlets (downward stream supply chain). Its management requires inter-organizational collaboration between the organization and its business partners. Today’s supply chain management software aims at improving collaborative planning, forecasting, and replenishment (CPFR) among companies in an extended supply chain. CPFR is not a specific information system. Rather, it is a business practice (or general reference model) well adopted in the retail, hard goods, apparel and consumer packaged goods, and chemical industries. Readers are referred to http://www.cpfr.com for a good introduction to the voluntary inter-industry commerce standards CPFR model. Based on a reference model such as CPFR, there are several well-known examples of specific IODSS in the USA. Among them, the asset management tool (AMT) of IBM Personal Systems Group and other divisions is a notable example (Lin et al, 2000). The AMT system consists of enterprise databases, advanced modeling, graphical user interface, simulation, and optimization capabilities for quantitative analysis of multiechelon inventory systems. There are a host of other companies worldwide who have implemented the CPFR model-based IODSS including Ace Hardware, Federated Department Stores, Proctor & Gamble (P&G), Warner-Lambert, Wal-Mart, Kmart, and Target in the USA and Dansk, Sainsbury, Tesco, and Superdrug in Europe. The essence of the CPFR model is sharing data/ information and business models among business partners and implementing a collaborative co-managed planning process. Especially, the success of this model critically hinges on sales forecasts made by a retailer, a supplier, a manufacturer, etc. Warner-Lambert Co., a division of Pfizer Inc., linked its planning DSS to Wal-Mart’s internal sales
PPL_JORS_2602140
12 Journal of the Operational Research Society Vol. ] ], No. ] ]
O
O
F
Bausch DO, Brown GG and Ronen D (1995). Consolidating and dispatching truck shipments of mobile heavy petroleum products. Interfaces 25: 1–17. Belz R and Mertens P (1996). Combining knowledge-bases systems and simulation to solve rescheduling problems. Decis Support Syst 17: 141–157. Bennett JL (ed) (1983). Building Decision Support Systems. Addison-Wesley: Reading, MA. Bermon S and Hood SJ (1999). Capacity optimization planning system (caps). Interfaces 29: 31–50. Bistline Sr WG, Banerjee S and Banerjee A (1998). RTSS: an interactive decision support system for solving real time scheduling problems considering customer and job priorities with schedule interruptions. Comput Opns Res 25: 981–995. Bonczek RH, Holsapple CW and Whinston AB (1981). Foundations of Decision Support Systems. Academic Press: New York. Bonini CP (1963). Simulation of Information and Decision Systems in the Firm. Prentice Hall: Englewood Cliffs. Borenstein D (1998). Idssflex: an intelligent DSS for the design and evaluation of flexible manufacturing systems. J Opl Res Soc 49: 734–744. Bowers MR and Agarwal A (1995). Lower in-process inventories and better on-time performance at Tanner Companies, Inc. Interfaces 25: 30–43. Brown G, Keegan J, Vigus B and Wood K (2001). The Kellogg company optimizes production, inventory, and distribution. Interfaces 31: 1–15. Buehlmann U, Ragsdale CT and Gfeller B (2000). A spreadsheetbased decision support system for wood panel manufacturing. Decis Support Syst 29: 207–227. Bui T, Yen J, Hu J and Sankaran S (2001). A multi-attribute negotiation support system with market signaling for electronic markets. Group Decis and Negotiation 10: 515–537. Butchers ER et al (2001). Optimized crew scheduling at Air New Zealand. Interfaces 31: 30–56. Campbell JF, Labelle A and Langevin A (2001). A hybrid travel distance approximation for a GIS-based decision support system. J Bus Logistics 22: 165–181. Carlsson C and Turban E (2002). DSS: directions for the next decade. Decis Support Syst 33: 105–110. Carravilla MA and de Sousa JP (1995). Hierarchical production planning in a make-to-order company: a case study. Eur J Opl Res 86: 43–56. Carroll WJ and Grimes RC (1995). Evolutionary change in product management: experiences in the car rental industry. Interfaces 25: 84–104. Chari K, Baker JR and Lattimore PK (1998). A decision support system for partial drug testing: DSS-dt. Decis Support Syst 23: 241–257. Chau PYK and Bell PC (1996). A visual interactive decision support system to assist the design of a new production unit. INFOR 34: 118–132. Chaudhry SS, Salchenberger L and Beheshtian M (1996). A small business inventory DSS: design, development, and implementation issues. Comput Opns Res 23: 63–72. Chen H-G and Sinha D (1996). An inventory decision support system using the object-oriented approach. Comput Opns Res 23: 153–170. Church RL, Murray AT, Figueroa MA and Barber KH (2000). Support system development for forest ecosystem management. 121: 247–258. Cosares S, Deutsch DN, Saniee I and Wasem OJ (1995). Sonet toolkit: a decision support system for the design of robust and cost-effective fiber-optic networks. Interfaces 25: 20–40.
TE
D
PR
mainframe. Just-in-time operational business intelligence (daily business intelligence) can be easily extracted on a realtime basis from on-line transaction processing systems and data warehouse. Thanks to the information technology infrastructure, many organizations are undergoing a fundamental shift in making their decisions. Today, many organizations build data warehouses, capturing and analysing massive data from data warehouse and transaction processing systems to support enterprise resource planning, enterprise planning and budgeting, customer relations management, supply chain management, etc. Our first survey (Eom and Lee, 1990, p. 65) concluded that ‘Despite two decades of cooperative efforts by practitioners and theoreticians to develop specific DSS, many goals in the DSS field remain unfulfilled. The critical issue is to implement a system that integrates organizational decision-making vertically (among strategic, tactical, and operational levels) and horizontally (among many functional fields at the same level) to coordinate and manage conflicts among various subunits of the organizations.’ These issues are not critical anymore, as the third survey indicates. Software vendors such as Oracle in the database management and business intelligence tools have now tightly integrated the database management software and business intelligence tools. Still there seems to be much more work needed to embed business intelligence functionality in the database in the case of Oracle (Vesset and Morris, 2004). We have made meaningful progress over the past several decades since the early 1970s. Nevertheless, more efforts should be made to develop theories, tools, techniques that can be applied in the development and implementation of DSS and that can meet the needs of practicing managers.
R
EC
Acknowledgements—We thank the editor and the anonymous referee whose suggestions improved the quality of the paper significantly. This research is in part supported by a research grant provided by Barney School of Business, University of Hartford.
R
References
U
N
C
O
Adenso-Dı´ az B, Gonzalez M and Garcı´ a E (1998). A hierarchical approach to managing dairy routing. Interfaces 28: 21–31. Alter SL (1980). Decision Support Systems: Current Practice and Continuing Challenges. Addison-Wesley: Reading, MA. Angehrn AA (1993). Computers that criticize you: stimulus-based decision support system. Interfaces 23: 3–16. Badri MA, Mortagy A, Davis D and Davis D (1997). Effective analysis and planning of r & d stages: a simulation approach. Int J Project Mngt 15: 351–358. Barba-Romero S (2001). The Spanish government uses a discrete multiplecriteria DSS to determine data-processing acquisitions. Interfaces 31: 123–131. Basnet C, Foulds L and Igbaria M (1996). Fleetmanager: a microcomputer-based decision support system for vehicle routing. Decis Support Syst 16: 195–207.
Q2
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 13
O
O
F
Foulds LR and Johnson DG (2000). Slotmanager: a microcomputer-based decision support system for university timetabling. Decis Support Syst 27: 367–381. Gryffenberg I et al (1997). Guns or butter: decision support for determining the size and shape of the south african national defense force. Interfaces 27: 7–28. Hess TJ, Rees LP and Rakes TR (2000). Using autonomous software agents to create the next generation of decision support systems. Decis Sci 31: 1–31. Heuter J and Swart W (1998). An integrated labor-management system for taco bell. Interfaces 28: 75–91. Huang JC-C, Culbreth CT, Joines JA, King RE and Hodgson TJ (1998). Decision support system for lumber procurement and dry kiln scheduling. Forest Products J 48: 51–59. Huntley CL, Brown DE, Sappington DE and Markowicz BP (1995). Freight routing and scheduling at CSX transportation. Interfaces 25: 58–71. Jarrah AIZ and Diamond JT (1997). The problem of generating crew bidlines. Interfaces 27: 49–64. Jiang JJ, Klein G and Pick RA (1998). A marketing category management system: a decision support system using scanner data. Decis Support Syst 23: 259–271. Ju¨ngen FJ and Kowalcyk W (1995). An intelligent interactive project management support system. Eur J Opl Res 84: 60–81. Katok E, Lathrop A, Tarantino W and Xu SH (2001a). Jeppesen uses a dynamic-programming-based DSS to manage inventory. Interfaces 31: 54–65. Katok E, Tarantino W and Tiederman R (2001b). Improving performance and flexibility at jeppesen: The world’s leading aviation-information company. Interfaces 31: 7–29. Keen PGW and Scott Morton MS (1978). Decision Support Systems: An Organizational Perspective. Addison-Wesley: Reading, MA. Kersten GE and Noronha SJ (1999). WWW-based negotiation support: design, implementation, and use. Decis Support Syst 25: 135–154. Kim Y-G, Kim H-W, Yoon J-W and Rhu H-S (1997). Building an organizational decision support system for korea telecom: a process redesign approach. Decis Support Syst 19: 255–269. Kobbacy A, Proudlove NC and Harper MA (1995). Towards an intelligent maintenance optimization system. J Opl Res Soc 46: 831–853. Kostuk KJ (1997). A decision support system for a large, multievent tournament. J Opl Res Soc 35: 183–195. Koutsoukis N-S, Dominguez-Ballesteros B, Lucas CA and Mitra G (2000). A prototype decision support system for strategic planning under uncertainty. Int J Phys Distribut Logistics Mngt 30: 640–652. Lambert DM and Cooper MC (2000). Issues in supply chain management. Indus Marketing Mngt 29: 65–84. Laudon KC and Laudon JP (2004). Management Information Systems: Managing the Digital Firm. Prentice Hall: Upper Saddle River, NJ. Leachman RC, Benson RF, Liu C and Raar DJ (1996). Impress: an automated production-planning and delivery-quotation system at Harris corporation-semiconductor sector. Interfaces 26: 6–37. LeBlanc LJ, Randels Jr D and Swan TK (2000). Heery international’s spreadsheet optimization model for assigning managers to construction projects. Interfaces 30: 95–116. Lee WJ and Lee KC (1999). Promise: a distributed DSS approach to coordinating production and marketing decisions. Comput Opns Res 26: 901–920. Lee YM and Chen EJ (2002). BASF uses a framework for developing Web-based production-planning-optimization tools. Interfaces 32: 15–24.
U
N
C
O
R
R
EC
TE
D
PR
Csa´ki P, Rapcsa´k T, Turcha´nyi P and Vermes M (1995). R and D for group decision aid in Hungary by wingdss, a microsoft windows based group decision support system. Decis Support Syst 14: 205–217. Curnow G et al (1997). Automating credit and collections decisions at AT&T capital corporation. Interfaces 27: 29–52. Datta S (1995). A decision support system for micro-watershed management in India. J Opl Res Soc 46: 592–603. Davis JG and Sundaram D (1995). Petaps: a prototype decision support system for consumer product marketing and promotion. Eur J Opl Res 87: 247–256. Degraeve Z and Schrage L (1998). Hop: a software tool for production scheduling at bridgestone/firestone off-the-road. Eur J Opl Res 110: 188–198. Desrosiers J, Lasry A, McInnis D, Solomon MM and Soumis F (2000). Air transat uses altitude to manage its aircraft routing, crew planning, and work assignment. Interfaces 30: 41–53. Dey PK (2001). Decision support system for risk management. Mngt Decis 39: 634–649. Dillon JE and Kontogiorgis S (1999). US airways optimizes the scheduling of reserve flight crews. Interfaces 29: 123–131. Dimopoulou M and Miliotis P (2001). Implementation of a university course and examination timetabling system. Eur J Opl Res 130: 202–213. Dutta S, Wierenga B and Dalebout A (1997). Designing management support systems using an integrative perspective. Commun ACM 40: 70–79. Eom HB and Lee SM (1990). A survey of decision support system applications (1971–April 1988). Interfaces 20: 65–79. Eom SB (2002a). Decision Support Systems Research (1970–1999): A Cumulative Tradition and Reference Disciplines. Edwin Mellen Press: Lewiston, New York. Eom SB (2002b). Extended enterprise decision support systems: a new frontier in the internet age. In: Adam F, Bre`zilion P, Humphreys P and Pomerol J-C (eds). Decision Making and Decision Support in the Internet age: Proceedings of DSIAGE2002, IFIP tc8/wg 8.3 Open Conference, University College Cork, Cork, Ireland, 4–7 July 2002. Oak Tree Press, Cork, Ireland, pp 726–739. Eom SB (2004). Evolution of DSS from single user DSS to interorganizational DSS. In: Eom SB (ed). Inter-organizational Information Systems in the Internet Age. Idea Group Publishing, Hershey, PA, pp 231–247. Eom SB, Lee SM, Kim EB and Somarajan C (1998). A survey of decision support system applications (1988–1994). J Opl Res Soc 49: 109–120. Espinasse B, Picolet G and Chouraqui E (1997). Negotiation support systems: a multi-criteria and multi-agent approach. Eur J Opl Res 103: 389–409. Fazlollahi B and Vahidov R (2001). A method for generation of alternatives by decision support systems. J Mngt Inform Syst 18: 229–250. Fierbinteanu C (1999). A decision support systems generator for transportation demand forecasting implemented by constraint logic programming. Decis Support Syst 26: 179–194. Forgionne GA (1997). HADTS: a decision support technology system to support army housing management. Eur J Opl Res 97: 369–379. Forgionne GA (2001). Hrsos: a decision support system to facilitate the privatization of military housing. J Opl Res Soc 52: 630–641. Forgionne GA and Kohli R (1996). HMSS: a management support system for concurrent hospital decision making. Decis Support Syst 16: 209–229.
PPL_JORS_2602140
14 Journal of the Operational Research Society Vol. ] ], No. ] ]
O
O
F
Pfeil G, Holcomb R, Muir CT and Taj S (2000). Visteon’s sterling plant uses simulation-based decision support in training, operations, and planning. Interfaces 30: 115–133. Price DHR et al (1998). A system to support the enhancement of strategic flexibility in manufacturing enterprises. Eur J Opl Res 109: 362–376. Raghunathan S (1999). Interorganizational collaborative forecasting and replenishment systems and supply chain implications. Decis Sci 30: 1053–1071. Rakshit A, Krishnamurthy N and Yu G (1996). System operations advisor: a real-time decision support system for managing airline operations at united airlines. Interfaces 26: 50–58. Ramani KV (2001). DSS-enabled materials management process at MP Trust hospital. Product Inventory Mngt 42: 1–11. Rangaswamy A and Shell GR (1997). Using computers to realize joint gains in negotiations: Toward an electronic bargaining table. Mngt Sci 43: 1147–1163. Riecken D (1994). Introduction to special issue on intelligent agents. 37: 18–21. Rigby B, Lasdon LS and Waren AD (1995). The evolution of Texaco’s blending systems: from omega to starblend. Interfaces 25: 64–83. Scott Morton MS (1971). Management decision systems: computerbased support for decision making. Division of Research, Harvard University, Cambridge, MA. Shim JP et al (2002). Past, present, and future of decision support technology. Decis Support Syst 33: 111–126. Shyur C-C and Wen U-P (2001). Sdhtool: planning survivable and cost-effective sdh networks at chunghwa telecom. Interfaces 31: 87–108. Sonntag C and Grossman Jr TA (1999). End-user modeling improves R&D management at Agrevo Canada, Inc. Interfaces 29: 132–142. Splettstoesser D and Splettstoesser M (1998). GSS-based environmental planning in Tanzania. J Global Inform Mngt 6: 26–34. Sprague Jr RH and Carlson ED (1982). Building Effective Decision Support Systems. Prentice Hall: Englewood Cliffs, NJ. Sycara K et al (1996). Distributed intelligent agents. IEEE Intelligent Systems 11: 36–46. Tavana M and Banerjee S (1995). Strategic assessment model (SAM): a multiple criteria decision support system for evaluation of strategic alternatives. Decis Sci 26: 119–143. Tavana M, Chung QB and Kennedy DT (1998). Rho: a decision support system for pricing in law firms. Inform Mngt 33: 155–165. Taylor RG, Vasu ML and Causby JF (1999). Integrated planning for school and community: the case of Johnston county, North Carolina. Interfaces 29: 67–89. Thierauf RJ (1982). Decision Support Systems for Effective Planning and Control: A Case Study Approach. Prentice Hall: Englewood Cliffs, NJ. Tracey M and Dror M (1997). Interactive graphical computer application for large scale cattle feed distribution management. Decis Support Syst 19: 61–72. Tsubone H, Matsuura H and Kimura K (1995). Decision support system for production planning–concept and prototype. Decis Support Syst 13: 207–215. U¨lengin F, Topcu YI and Sahin S (2001). An integrated decision aid system for bosphorus water-crossing problem. Eur J Opl Res 134: 179–192. Vesset D and Morris HD (2004). Why consider Oracle for business intelligence? White Paper, IDC (International Data Corporation, www.idc.com ), pp 1–12.
U
N
C
O
R
R
EC
TE
D
PR
Levin N, Zahavi J and Olitsky M (1995). Amos-a probabilitydriven, customer-oriented decision support system for target marketing of solo mailings. Eur J Opl Res 87: 708–721. Li S (2000). The development of a hybrid intelligent system for developing marketing strategy. Decis Support Syst 27: 395–409. Lim JS and O’Connor M (1996). Judgmental forecasting with interactive forecasting support systems. Decis Support Syst 16: 339–357. Lim L-H and Benbasat I (1992-1993). A theoretical perspective of negotiation support systems. J Mngt Inform Syst 9: 27–44. Lin G et al (2000). Extended-enterprise supply-chain management at IBM personal systems group and other divisions. Interfaces 30: 7–25. Madu CN, Kuei C-H and Chen J-H (1995). A decision support systems approach to adjust maintenance float system availability levels. Comput Indust Eng 28: 773–786. Mak H-Y, Mallard AP, Bui T and Au G (1999). Building online crisis management support using workflow systems. Decis Support Syst 25: 209–224. Mallya S, Banerjee S and Bistline WG (2001). A decision support system for production/distribution planning in continuous manufacturing. Decis Sci 32: 545–556. Mantrala MK and Rao S (2001). A decision-support system that helps retailers decide order quantities and markdowns for fashion goods. Interfaces 31: 146–165. Mathaisel DFX (1996). Decision support for airline system operations control and irregular operations. Comput Opns Res 23: 1083–1098. Matsatsinis NF (1995). An intelligent decision support system in marketing: support methodology and integrated architecture. Ph.D. Thesis (in Greek). McHaney RW and Douglas DE (1997). Multivariate regression metamodel: a DSS application in industry. Decis Support Syst 19: 43–52. Mitropoulos S, Assimakopoulos V and Charalabidis Y (1995). Two-dimensional color pattern load analysis: a tool supporting demand-side management. Decis Support Syst 13: 159–166. Mohan L, Muse L and McInerney C (1998). Management smarter: a decision support system for mental health providers. J Behaviour Health Ser Res 25: 446–454. Monplaisir LF, Benjamin CO and Lu C (1997). Innovative applications of groupware for solving engineering design problems. Eng Mngt J 9: 11–16. Murthy S et al (1999). Cooperative multiobjective decision support for the paper industry. Interfaces 29: 5–30. Mustajoki J and Ha¨ma¨la¨inen RP (2000). Web-hipre: global decision support by value tree and ahp analysis. INFOR 38: 208–220. Nardi BA, Miller JR and Wright DJ (1998). Collaborative programmable intelligent agents. Commun ACM 41: 96–104. Nemhauser GL (1993). The age of optimization: solving large-scale real world problems. The 1993 Phillip McCord Morse Lecture, May 7, 1993, TIMS/ORSA Joint National Meeting, Chicago, IL. Nussbaum M et al (1999). Decision support system for conflict diagnosis in personnel selection. Inform Mngt 36: 55–62. O¨zdamar L and Birbil SI (1999). A hierarchical planning system for energy intensive production environments. Int J Product Econom 58: 115–129. Ozer M (1999). The use of Internet-based groupware in new product forecasting. Int J Market Res 41: 425–438. Palma-dos-Reis A and Zahedi FM (1999). Designing personalized intelligent financial decision support systems. Decis Support Syst 26: 31–47.
Q3
PPL_JORS_2602140
S Eom and E Kim—A survey of decision support system applications (1995–2001) 15
Wilkenfeld J, Kraus S, Holley KM and Harris MA (1995). Genie: a decision support system for crisis negotiations. Decis Support Syst 14: 369–391. Zopounidis C and Doumpos M (2002). Multi-criteria decision aid in financial decision making: Methodologies and literature review. J Multicriteria Decis Anal 11: 167–186.
Received February 2005; accepted October 2005 after one revision
U
N
C
O
R
R
EC
TE
D
PR
O
O
F
Wagner C and Turban E (2002). Are intelligent e-commerce agents partners or predators? Commun ACM 45: 84–90. Wang H, Liao S and Liao L (2002). Modeling constraint-based negotiating agents. Decis Support Syst 33: 201–217. Wierenga B and Van Bruggen GH (2001). Developing a customized decision-support system for brand manager. Interfaces 31: 128–145. Wierzbicki AP and Granat J (1999). Multi-objective modeling for engineering applications: Didasn þ þ system. Eur J Opl Res 113: 374–389.
