Download Part 2: Decision Support Systems

CHAPTER 3
Decision Support Systems:
An Overview
1
3.1 DSS configurations
Strategic planning is one of the most important tasks of modern
management. It involves all functional areas in an
organization and several relevant outside factors, a fact that
complicates the planning process, especially in dealing with
long-rum uncertainties. Thus, strategic planning is clearly not
a structured decision situation, so it is potential candidate for
DSS application.
The Gotass-Larsen Shipping Corp. (GLSC), subsidiary of
International Utilities (IU), operates cargo ships all over the
world. The company developed a comprehensive DSS for
performing both short-and long-term planning. The system is
composed of two major parts: data and models.
The data include both external data (port or cannel
characteristics, competitor’s activities, and fares) and
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-2
3.1 DSS configurations
internal data (existing plans, availability of resources, and
individual ship’s characteristics). In addition, users can
incorporate their own data or express their attitudes (for
example, by adding their own risk assessments).
The models include routine standard accounting and
financial analysis model (such as cash flow computations
and pro forma income and expenses) organized on a per
ship, per voyage, per division, and company-wide basis.
These models permit elaborate financial analyses. A
simulation model is used to analyze short- and long-term
plans and to evaluate the desirability of projects. In
addition, the system interfaces with a commercially
available application program for analyzing individual
voyages.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-3
3.1 DSS configurations
A highly decentralized 15 month operational planning and
control document is prepared within the framework of the
long-term strategic plan. This document is used as the basis
for detailed goal formation for the various ships and
individual voyages. A detailed monitoring and control
mechanism is also provided, including a regular variance
report and diagnostic analysis. In addition, a detailed
performance tracking report is executed (by voyage, ship,
division, and entire corporation).
Once the assessment of the opportunity of individual
projects (such as contracting a specific voyage) is
examined, an aggregation is performed. The objective is to
determine whether a series of individually profitable project
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-4
3.1 DSS configurations
Adds to feasible and effective long-range plan. The DSS uses
a simulation model that examines various configurations of
projects in an attempt to fine-tune the aggregate plan.
Specifically, when several projects are selected, resources
might be insufficient for all projects. Therefore,
modifications in scheduling and financial arrangements
might be necessary. This fine-tuning provides a trial-anderror approach to feasibility testing and sensitivity analyses.
The what-if capabilities of the DSS are especially important
in this case because a trial-and-error approach to managing
the organization would be disastrous. The strategic plan of
GLSC is very detailed and accurate because of the
contractual nature of the sales and some of the expenses.
The model is geared to a traditional business policy
structure, which helps in assessing the threats and risks in
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-5
3.1 DSS configurations
The general operating environment and makes possible an
examination of the impacts of new opportunity on existing
plans.
This is an example of large-scale, strategic DSS. We refer to
this vignette throughout this chapter.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-6
3.1 DSS configurations











Supports individuals and teams
Used repeatedly and constantly
Two major components: data and models
It supports several interrelated decisions
Web-based
It uses both internal and external data
Uses subjective, personal, and objective data
Has a simulation model
Used in public and private sectors
Has what-if capabilities
Uses quantitative and qualitative models
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-7
3.1 DSS configurations
This vignette demonstrates some of the potential
diversification of DSS. Decision support can be provided
in many different configurations. These configurations
depend on the nature of the management decision situation
and the specific technologies used for support. These
technologies are assembled from four basic components
(each with several variations): data, models, knowledge,
and user interface. Each of these components is managed
by software that either is commercially available or must
be programmed for the specific task. The manner in which
these components are assembled defines their major
capabilities and the nature of the support provided. For
example, models are emphasized in a model-oriented
DSS, as in the opening vignette. Such models can be
customized with a modeling language (such as
spreadsheet) or can be provided by standard algorithmtools such All
asRight
linear
Fall,based
2006
Reserved, Yao Zhong, School of E&M, BUAA
3-8
3.2 What is a DSS
programming. Similarly, in a data-oriented DSS, a database
(or data warehouse) and its management play the major
role.
DSS definitions
We have defined the DSS in chapter 1 like this:
Decision support systems couple the intellectual resources of
individuals with the capabilities of the computer to
improve the quality of decisions. It is a computer based
support system for management decision makers who deal
with semistructured problems (Keen and Morton,1987).
Why do we redefine it in this chapter?

Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-9
3.2 What is a DSS
Why do we redefine it in this chapter?
Keen and Morton’s definition is identified as a system
intended to support managerial decision makers in
semistructured decision situations. DSS were meant to be
an adjunct to decision makers, to extend their capabilities
but not to replace their judgment. It is a computer-based
system.
Several other definitions appeared that caused considerable
disagreement as to what really is a DSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-10
3.2 What is a DSS

Little (1970)
“model-based set of procedures for processing data and
judgments to assist a manager in his decision making”
Assumption: that the system is computer-based and
extends the user’s problem-solving capabilities.

Alter (1980)
Contrasts DSS with traditional EDP(electronic data
processing) systems (Table 3.1)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-11
TABLE 3.1 DSS versus EDP.
Dimension
DSS
EDP
Use
Active
Passive
User
Line and staff management
Clerical
Goal (final)
Effectiveness
Mechanical
efficiency
Time
Horizon
Present and future
Past
Objective
Flexibility
(detail things)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
Consistency
3-12
Moore and Chang (1980)
1. Extendible systems
2. Capable of supporting ad hoc data analysis and
decision modeling
3. Oriented toward future planning
4. Used at irregular, unplanned intervals

Bonczek et al. (1980)
A computer-based system consisting of
1. A language system -- communication between the user
and DSS components
2. A knowledge system
3. A problem-processing system--the link between the other
two components

Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-13
 Keen (1980)
DSS apply “to situations where a ‘final’ system can be
developed only through an adaptive process of learning
and evolution”
 Central Issue in DSS
support and improvement of decision making
These definitions are compared and contrasted by
examining the various concepts used to define DSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-14
TABLE 3.2 Concepts Underlying DSS Definitions.
Source
Gorry and Scott Morton
[1971]
DSS Defined in Terms of
Problem type, system function
(support)
Little [1970]
System function, interface
characteristics
Alter [1980]
Usage pattern, system objectives
Moore and Chang [1980]
Usage pattern, system capabilities
Bonczek, et al. [1996]
Keen [1980]
System components
Development process
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-15
3.2 What is a DSS

Working Definition of DSS
 A DSS is an interactive, flexible, and adaptable CBIS,
specially developed for supporting the solution of a
non-structured management problem for improved
decision making. It utilizes data, it provides easy user
interface, and it allows for the decision maker’s own
insights

Fall, 2006
DSS may utilize models, is built by an interactive
process (frequently by end-users), supports all the
phases of the decision making, and may include a
knowledge component
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-16
3.3 Characteristics and Capabilities
of DSS
1. Provide support in semi-structured and unstructured
situations, includes human judgment and computerized
information
2. Support for various managerial levels (top to line
manager)
3. Support to individuals and groups
4. Support to interdependent and/or sequential decisions
5. Support all phases of the decision-making process
6. Support a variety of decision-making processes and styles
(more)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-17
7. Are adaptive
8. Have user friendly interfaces
9. Goal: improve effectiveness of decision making
10. The decision maker controls the decision-making
process
11. End-users can build simple systems
12. Utilizes models for analysis
13. Provides access to a variety of data sources, formats,
and types, ranging from geographic information
systems to object-oriented ones.
Decision makers can make better, more consistent
decisions in a timely manner.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-18
3.4 DSS Components
1. Data Management Subsystem
Includes the database, which contains relevant data for
the situation and is managed by software called
DBMS.
2. Model Management Subsystem
A software package that includes financial, statistical,
management science, or other quantitative models that
provides the system’s analytical capabilities and
appropriate software management. Modeling language
for building custom models are also included. This is
often called a MBMS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-19
3.4 DSS Components
3. Knowledge-based (Management) Subsystem
This subsystem can support any of the other
subsystems or act as an independent component. It
provides intelligence to augment the decision maker’s
own.
4. User Interface Subsystem
The user communicates with and commands the DSS
through this subsystem.
5. The User
is considered to be part of system. Researchers assert
that some of the unique contributions of DSS are
derived from the intensive interaction between the
computer and the decision makers.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-20
Other Computer-based
systems
Data: external
and internal
Data
Management
Model
Management
Knowledge
Management
User
Interface
Manager
(user)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-21
3.5 The Data Management Subsystem

DSS database
A database is a collection of interrelated data organized to
meet the need and structure of an organization and can be
used by more than one person for more than one
application. There are several possible configurations for
a database. For lager DSS, the database is basically
included in the data warehouse (next chapter). For some
applications, a special database is constructed as needed.
Several databases may be used in one DSS application,
depending on the data sources. Data is extracted from
internal and external data sources, as well as personal
data belonging to one or more users. (Figure 3.3)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-22
Internal Data Source
External Data
Source
Finance
Marketing
Extraction
Query
Facility
Production
Personnel
Other
Private, personal
data
Decision Support
database or
data warehouse
DBMS
Interface
Management
•Retrieval
Data
Directory
•Inquiry
Model
Management
•Update
•Report
Knowledge
Management
•Delete
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-23
3.5 The Data Management Subsystem
Internal data come mainly from the organization’s
transaction processing system. Example are payroll
monthly. Other internal data are machine maintenance
scheduling, forecasts of future sales, cost of out-of-stock
items, and future hiring plans. Some times internal data
are made available through Web browser over an
Internet, an internal Web-based system.
External data may include industry data, marketing
research data, census data, regional employment data,
government regulations, tax rate schedules, or national
economic data. Internet also is an important data
sources.
Private data may include guidelines used by specific
decision makers and assessment of specific data or
situations.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-24
3.5 The Data Management Subsystem
Data Organization
Should a DSS have an independent database? It
depends. In small ad hoc DSS, data can be entered
directly into models sometimes extracted directly from
larger database. The organization’s data warehouse is
often used for building DSS applications. Some large
DSS have their own fully integrated, multiple-source
DSS databases. A separate DSS database need not be
physically separate from the corporate database. They
can be physically stored together for economic reasons.
A DSS database can also share a DBMS with other
systems. A DSS database may include multimedia
objects (such as pictures, maps, or sounds). An objectoriented database is found in some recent DSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-25
3.5 The Data Management Subsystem
Extraction
To create a DSS database, or a data warehouse, it is
often necessary to capture data from several sources.
This operation is called extraction. It is basically the
importing of files, summarization, filtration, and
condensation of data. Extraction also occurs when the
user produces reports from the data in the DSS database.
The extraction process is managed by a DBMS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-26
3.5 The Data Management Subsystem
Database
management system
The data base is created, accessed, and updated by a DBMS.
Most DSS are built with a standard commercial DBMS that
provides capabilities such as those shown in the following list:
Captures/extracts data for inclusion in a DSS database
Updates (adds, deletes, edits, changes) data records and
files
Interrelates data from different sources
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-27
3.5 The Data Management Subsystem
 Retrieves data from the database for queries and reports
Provides comprehensive data security (protection from
unauthorized access, recovery capabilities, etc.)
Handles personal and unofficial data so that users can
experiment with alternative solutions based on their own
judgment
Performs complex data manipulation tasks based on queries
Tracks data use within the DSS
Manages data through a data dictionary
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-28
3.5 The Data Management Subsystem

Data directory
Data directory is a catalog of all the data in the database. It
contains the data definitions, and its main function is to
answer questions about the availability of data items, their
source, and their exact meaning. The directory especially
appropriate for supporting the intelligence phase of the
decision-making process by helping scan data and identify
problem areas or opportunities. The directory, like any other
catalog, supports the addition of new entries, deletion of
entries, and retrieval of information on specific object.

Query facility
In building and using DSS, it is often necessary to access,
manipulate, and query the data. The Query facility performs
all these tasks. It accepts requests for data from other DSS
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-29
3.5 The Data Management Subsystem

Query facility
components, determine how these requests can be filled,
formulates the detailed requests, and returns the results to the
issuer of the request. The query facility includes a special
query language. Important functions of a DSS query system
are the selection and manipulation operations.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-30
3.5 The Data Management Subsystem

Data Management Issues
– Data warehouse
– Data mining
– Special independent DSS databases
– Extraction of data from internal, external, and private
sources
– Web browser data access
– Web database servers
– Multimedia databases
– Special GSS databases (like Lotus Notes / Domino
Server)
– Online Analytical Processing (OLAP)
– Object-oriented databases
– Commercial database management systems (DBMS)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-31
3.6 The Model Management Subsystem

Analog of the database management
subsystem
(Figure on next slide )

Model base
Model base management system
Modeling language
Model directory
Model execution, integration, and command
processor




Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-32
3.6 The Model Management Subsystem
Models (Model Base)
•Stratigic, tactical,operational
Model
•Statistical, Financial,
marketing,MS, Accounting,
engineering,etc.
Directory
•Model building blocks
Model Base Management
Model execution,
•Modeling commands: creation
Integration, and command
processor
•Maintenance:update
•DB interface
•Modeling language
Data
Management
Fall, 2006
Interface
Management.
Knowledge
management
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-33
3.6 The Model Management Subsystem
Model Base
A model base contains routine and special statistical,
financial, forecasting, management science, and other
quantitative models that provide the analysis capabilities in
a DSS. The ability to invoke, run, change, combine, and
inspect models is a key DSS capability that differentiates it
from other CBIS. The models in the model base can be
divided into four major categories: strategic, tactical,
operational, and model-building blocks and routine.
Strategic Models: are used to support top management’s
strategic planning responsibilities. Potential applications
include developing corporate objectives, planning for
mergers and acquisitions, plant location
selection,environmental impact analysis, and nonroutine
capital budgeting.

Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-34
3.6 The Model Management Subsystem
form. Mostly external data are used. The GLSC opening
vignette includes a long-range planning model.
Tactical Models: are used mainly by middle management to
assist in allocating and controlling the organization’s
resources. Examples of tactical models include labor
requirement planning, sales promotion planning, plant
layout determination, and routine capital budgeting.
Tactical models are usually applicable only to an
organizational subsystem such as the accounting
department. Their time horizon varies from 1 month to less
than 2 years. Some external data are needed, but the
greatest requirements are for internal data. The GLSC
vignette includes some tactical models for its 15 months
plan.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-35
3.6 The Model Management Subsystem
Operational Models: are used to support the day-to-day
working activities of the organization. Typical decisions
are approving personal loans by a bank, production
scheduling, inventory control, maintenance planning and
scheduling, and quality control. Operational models
support mainly manager’s decision making with a daily to
monthly time horizon. These models normally use internal
data.
The models in the model base can also be classified by
functional areas ( such as financial models or production
control models) or by discipline (such as statistical model,
or management science allocation models). The number of
models in a DSS can vary from a few to several hundred.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-36
3.6 The Model Management Subsystem

Modeling Language
Because DSS deal with semistructured or unstructured
problems, it is often necessary to customize models. This
can be done with high-level languages. Some examples of
these are COBOL, with a spreadsheet or with other fourthgeneration languages, and special modeling language such
as IFPS/Plus.
The Model Base Management System (MBMS)
The functions of the model base management system
(MBMS) software are model creation using subroutine and
other building blocks, generation of new routine and
reports, model updating and changing, and model data
manipulation. The MBMS is capable of interrelating
models with the appropriate linkages through a database.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-37
3.6 The Model Management Subsystem

Major Functions of the MBMS







Fall, 2006
Creates models easily and quickly, either from scratch
or from existing models or from the building blocks
Allows users to manipulate the models so they can
conduct experiments and sensitivity analysis ranging
from what-if to goal seeking.
Stores, retrieves, and manages a wide variety of
different types of models in a logical and integrated
manner
Accesses and integrates the model building blocks
Catalogs and displays the directory of models for use
by several individuals in the organization
Tracks model data and application use
Interrelates models with appropriate linkages with the
database and integrates them within the DSS
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-38
3.6 The Model Management Subsystem

Major Functions of the MBMS



Manages and maintains the model base with
management functions analogous to database
management: store, access, run, update link ,catalog,
and query
Uses multiple models to support problem solving
The Model Directory
The role of the model directory is similar to that of a database
directory. It is a catalog of all the models and other
software in the model base. It contains the model
definitions, and its main function is to answer questions
about the availability and capability of the models.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-39
3.6 The Model Management Subsystem

Model Execution, Integration, and Command
The following activities are usually controlled by model
management:
– Model execution is the process of controlling the actual
running of the model.
– Model integration means combining the operations of
several models when needed (such as directing the
output of one model to be processed by another one).
– A model command processor is used to accept and
interpret modeling instructions from the dialog
component and to rout them to the MBMS, the model
execution, or the integration functions.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-40
3.6 The Model Management Subsystem

Model Management Issues
–
Model level: Strategic, managerial (tactical), and
operational
–
Modeling languages
–
Lack of standard MBMS activities. WHY?
–
Use of AI and fuzzy logic in MBMS
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-41
3.7 The Knowledge Based (Management)
Subsystem




Provides expertise in solving complex unstructured and
semi-structured problems
Expertise provided by an expert system or other intelligent
system
Advanced DSS have a knowledge based (management)
component that can provide the required expertise for
solving some aspects of problem and providing knowledge.
Silverman [1995] suggested that:



Fall, 2006
knowledge-based decision aids (support unaddressed problem with
mathematics)
Intelligent decision modeling systems (build, apply and manage
libraries of models)
Decision analytic expert systems (integrate theoretically rigorous
methods of uncertainty into the expert system knowledge bases)
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-42
3.7 The Knowledge Based (Management)
Subsystem


Knowledge-based DSS can be called intelligent DSS, or
DSS/ES, expert support system, or simply knowledge-based
DSS.
Data mining application can be one of them.
Knowledge worker
I –access services
Authentication; Translation and transformation for diverse
applications and appliances (e.g., browser, PIM, file
system, PDA, mobile phone
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-43
II – Personalization service
Personalized knowledge portals; profiling; push-service; process-;
project-; or role-oriented knowledge portals
III – Knowledge service
Discovery
Publication
Collaboration
Learning
Search, mining,
knowledge maps,
navigation,
visualization
Formats, structuring,
contextualization,
workflow, oauthoring
Skill/expertise mgmt,
community space,
experience mgmt,
awareness mgmt.
Authoring, course
mgmt, tutoring,
learning paths,
examinations
IV –Integration service
Taxonomy, knowledge structure, ontology; multi-dimensional metadata
(tagging); directory services; synchronization services.
V –Infrastructure service
Intranet infrastructure service; groupware services; extract;
transformation; loading; inspection service.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-44
(1)
(2)
(3)
(4)
(5)
(6)
VI- data and knowledge source
(1) Intranet/extranet, Messages, contents of CMS, elearning platforms
(2) DMS documents, files from office information systems,
(3) Data from RDMS, TPS, data warehouse,
(4) Personal information management data
(5) Content from Internet, WWW, newsgroups
(6) Data from external online database
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-45
3.8 The User Interface (Dialog)
Subsystem
 Includes all communication between a user and the
MSS
 Graphical user interfaces (GUI)
 Voice recognition and speech synthesis possible
 To most users, the user interface is the system
 Management of the User Interface Subsystem
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-46
3.8 The User Interface (Dialog)
Subsystem
 Management of the User Interface Subsystem
This subsystem is managed by software called the user
interface management system(UIMS)
 UIMS capabilities:
– Provides graphical user interface
– Accommodates the user with a variety of input devices
– Presents data with a variety of formats and output devices
– Gives users help capabilities, prompting, diagnostic and
suggestion routines, or any other flexible support
– Provides interactions with the database and the model base
– Stores input and output data
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-47
3.8 The User Interface (Dialog)
Subsystem
UIMS capabilities:
– Provides color graphics, three-dimensional graphics, and
data plotting
– Has windows to allow multiple functions to be displayed
concurrently
– Can support communication among and between users and
building of MSS
– Provides training by example (guiding user through the
input and modeling process)
– Provides flexibility and adaptiveness so the MSS can
accommodate different problems and technologies
– Interacts in multiple, different dialog styles
– Captures, stores, and analyzes dialog usage to improve the
dialog system
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-48
3.8 The User Interface (Dialog)
Subsystem
The User Interface Process
Figure 3.5 shows the process for an MSS. The user interacts
with the computer via an action language processed via the
UIMS. In advanced system the user interface component
includes a natural language processor or may use standard
objects (such as poll-down menu and buttons) through a
graphical user interface (GUI). The UIMS provides the
capabilities listed in DSS in Focus 3.5 and enables the user to
interact with the model management and data management
subsystems.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-49
Data
Management and
DBMS
Knowledge
Management
Model
Management and
MBMS
User Interface
Management Sys.
UIMS
Natural Language
Processor.
Action
Language
Display
Language
Terminal
Printers, Plotters
User
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-50
3.9 The User
The person faced with the decision that the MSS is
designed to support is called the user, the
manager, or the decision maker
 Two board classes:
Managers
– Staff specialists: e.g. Financial analysts, production
planners, etc.
Intermediaries: the connectors between manager and DSS
1. Staff assistant
2. Expert tool user
3. Business (system) analyst
4. GDSS Facilitator
 In detail,
–

Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-51
3.9 The User
1. Staff assistant: has specialized knowledge about management
problems and some experience with decision support
technology
2. Expert tool user: is skilled in the application of one or more
types of specialized problem-solving tools.
3. Business (system) analyst: has a general knowledge of the
application area, a formal business administrator education (not
computer science), and considerable sill in DSS construction
tools.
4. GDSS Facilitator: controls and coordinates the software of
GDSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-52
3.10 DSS Hardware

Evolved with computer hardware and
software technologies

Major Hardware Options
– Mainframe
– Workstation
– Personal computer
– Web server system
• Internet
• Intranets
• Extranets
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-53
3.11 Distinguishing DSS from
Management Science and MIS

MIS can be viewed as an IS infrastructure that can
generate standard and exception reports and summaries,
provide answers to queries, and help in monitoring and
tracking. It is usually organized along functional areas.
Thus, there are marketing MIS, accounting MIS, and so
on. A DSS, on the other hand, is basically a problemsolving tool and it is often used to address ad doc and
unexpected problems. MIS is usually developed by the IS
department because of its permanent infrastructure nature.
DSS is usually and end-user tool; it can provide decision
support within a short time. An MIS can provide quick
decision support only to situations for which the models
and software were prewritten.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-54
3.11 Distinguishing DSS from
Management Science and MIS


Because of its unstructured nature, DSS is usually
developed by a prototype approach. MIS, on the other
hand, is often developed by a structured methodology
such as the system development life cycle (SDLC)
A DSS can evolves as the decision maker learn more
about the problem. Often managers cannot specify in
advance what they want from computer programmers and
model builders. Many computerized applications are
developed in a way that requires detailed specifications to
be formalized in advance. This requirement is not
reasonable in many semistructured and unstructured
decision-making tasks.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-55
3.11 Distinguishing DSS from
Management Science and MIS
The Major characteristics of MIS, MS, and DSS:
 MIS:
 The main impact has been on structured tasks, where
standard operating procedures, decision rules, and
information flows can be reliably redefined.
 The main payoff has been in improving efficiency by
reducing costs, turnaround time, and so on, and by
replacing clerical personnel.
 The relevance for manager’s decision making has
mainly been indirect ( for example, by report and
access the data)
 MS/OR
 The impact has mostly been on structured problems
(rather than tasks), where the objective, data, and
constraints can be pre-specified.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-56
3.11 Distinguishing DSS from
Management Science and MIS





The payoff has been in generating better solutions for
given types of problems.
The relevance for manager’ has been the provision of
detailed recommendations and new methods for handling
complex problems.
DSS
the impact is on decisions in which there is sufficient
structure for computer and analytic aids to be of value but
where the manager’s judgment is essential.
The payoff is in extending the range and capability of
manager’s decision processes to help them improve their
effectiveness
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-57
3.11 Distinguishing DSS from
Management Science and MIS


The relevance for manager is the creation of a supportive
tool, under their own control, that dose not attempt to
automate the decision process, predefine objectives, or
impose solutions.
Example, Marketing DSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-58
Standard Statistical
Models
Marketing
data
Regresssion analysis
Factor analysis
Sales Reports
Market
reports
Cluster analysis
Discriminant analysis
Government
reports
…
Standard MS Models
Linear Programming
Marketing
model
Media Mix
Site Location
Advertising
budget
Marketing
recommendati
ons &
evaluation
Product Design
….
Markov analysis
Decision table
database
Inventory
User Interface
User
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-59
3.12 DSS Classifications

Alter’s Output Classification (1980)
Degree of action implication of system outputs
(supporting decision) (Table 3.4)
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-60
OrientationCategory
Data
File drawer
system
Data analysis
systems
Data or
Model
Models
Type of
Operation
Type of Task
Access data items Operational
Ad hoc analysis
of data files
Operational,
analysis
Analysis
information
systems
Ad hoc analysis Aanlysis,
involving multiple Planning
databases and
small models
Accounting
Standard calcula- Planning
Models
tions that estiBudgeting
mate future
results on the
basis of accounting definitions
Representation Estimating
Planning
Models
consequences of Budgeting
particular actions
Optimization
Models
Suggestion
Models
Fall, 2006
Calculation an
optimal solution
to a combinatorial problem
Performing calculation that generate a suggested
decision
Planning,
Resource
allocation
Operational
User
Nonmanagerial
line personnel
Staff analysis or
managerial line
personnel
Staff analyst
Usage pattern
Simple inquires
Staff analyst
Input possible
decision; receive
estimated results
as output
input constraints
and objectives;
receive answer
Time Frame
Irregular
Manipulation and Irregular
display of data
or periodical
Programming spe- Periodic
cial reports, developing small
models
Staff analyst or Input estimate of Periodic
manager
activity: receive or irregular
estimated monetary results as
output
Staff analyst
Periodic
or irregular
Periodic
or irregular
Nonmanagerial Input a structured daily or periodic
line personnel decription of the
decision situation
receive a suggested
decsion
as output
All Right Reserved, Yao Zhong, School of E&M,
BUAA
3-61
3.12 DSS Classifications

Holsapple and Whinston’s Classification [1996]
1. Text-oriented DSS
Information (including data and knowledge) is often stored in a
textual format and must be accessed by the decision makers. The
amount of information to be searched by the decision makers is
exponentially growing. Therefore, it is necessary to represent and
process text documents and fragments effectively and efficiently.
A text-oriented DSS supports a decision maker by electronically
keeping track of texually represented information that could have
a bearing on decisions. It allows documents to be electronically
created, revised, and viewed as needed. Information technologies
such as document imaging, hypertext, and intelligent agents can
be incorporated into the text-oriented DSS application. New
Web-based systems are revolutionizing the development and
deployment of text-oriented DSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-62
3.12 DSS Classifications
2. Database-oriented DSS
Database plays a major role in the DSS structure. Rather than
being treated as streams of text, data are organized in highly
structured format (relational or objective-oriented). The
early generations of database-oriented DSS used mainly the
relational database configuration. The information handled
by relational databases tends to be voluminous, descriptive,
and rigidly structured. Database-oriented DSS features
strong report generation and query capability
3. Spreadsheet-oriented DSS
A spreadsheet is a modeling language that allows the user to
write models to execute DSS analysis. These not only
create, view, and modify procedural knowledge, but also
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-63
3.12 DSS Classifications
instruct the system to execute their self-contained
instructions. Spreadsheets are widely used in end-user
developed DSS. The most popular end-user tools for
developing DSS are Microsoft Excel and Lotus 1-2-3,
both of which are spreadsheets.
Because package such Excel can include a rudimentary
DBMS, or can readily interface with one, such as Access,
they can handle some properties of a database-oriented
DSS, especially the manipulation of descriptive
knowledge. Some spreadsheet development tools include
what-if analysis and goal-seeking capabilities and they are
revisted in Chapter 5.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-64
3.12 DSS Classifications
4. Solver-oriented DSS
A solver is an algorithm or procedure written as a
computer program for performing certain computation for
solving a particular problem type. Examples of a solver
can be an economic order quantity procedure for
calculating an optimal ordering quantity or a linear
regression routine for calculating trend.
5. Rule-oriented DSS
The knowledge component of DSS described earlier
includes both procedural and inferential (reasoning) rules,
often an expert system. These rules can be qualitative or
quantitative. This application of artificial intelligence is
describes in Chapter 6.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-65
3.12 DSS Classifications
6. Compound DSS
A compound DSS is a hybrid system that includes two or
more of the five basic structured described above. A
compound DSS can be built by using a set of independent
DSS, each specializing in one area. A compound DSS can
also build as a single, tightly integrated DSS.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-66
3.13 Other Classifications

Institutional DSS vs. Ad Hoc DSS

Institutional DSS deals with decisions of a
recurring nature
Example, a portfolio management system, GLSC
vignette.
 Ad Hoc DSS deals with specific problems that
are usually neither anticipated nor recurring.
Often involving strategic planning and
sometimes management control problems.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-67
3.13 Other Classifications




Degree of nonprocedurality (Bonczek et al., 1980)
BASIC and COBOL language called procedure language,
most non-procedure language is used in DSS building.
This non-procedure language is four generation language
(4GL)
Personal, group, and organizational support
(Hackathorn and Keen, 1981)
Individual versus group support systems (GSS)
Custom-made versus ready-made systems
Ready-made systems: Some organizations such as school ,
hospital, banks etc. have similar problems to be solved.
Building a DSS can be used (mirror modification) in
several organizations. Such DSS called ready-made
systems.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-68
Individual Assignment





1. How to distinguish DSS from MS and MIS?
2. According to Alter [1980], how to Classify DSS?.
3. What are the relationships and distinguishes between
Alter’s [1980] classification and Holsapple and
Whinston’s [1996] classification about DSS?
4. What components does a DSS have? Briefly
describing functions of each component in DSS.
What are the model-oriented DSS and data-oriented
DSS?
Group Assignment (option)
Design a DSS framework for the case of this chapter open
vignette, that is Gotaas-Larsen Shipping Gorp.
Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-69
Individual Assignment
3. What are the relationships and distinguishes between Alter’s
[1980] classification and Holsapple and Whinston’s [1996]
classification about DSS?
Distinguish: Alter’s classification is based the “degree of action
implication of system output”, or system output can directly
support (or determine the decision). H&P classification is based
on the applications or processing objectives.
Relationships: According to Alter’s classification, there are seven
categories: the first two types are data oriented, performing
data retrieval or analysis, which is correspond to the H&P’s
Text- and Database-oriented DSS; the third deals with data and
models (H&P:database, Spreadsheet). The reminders are model
oriented, providing either simulation capabilities, optimization,
or computations that suggest an answer (solver- and ruleoriented DSS). Not every DSS fits neatly into a single
classification system. Some have equally strong data and
modeling orientation

Fall, 2006
All Right Reserved, Yao Zhong, School of E&M, BUAA
3-70