Chapter 9

Decision Support Systems

McGraw-Hill/Irwin Copyright © 2010 by the McGraw-Hill Companies, Inc. All rights reserved.
 Learning Objectives

 Identify the changes taking place in the form

and use of decision support in business

 Identify the role and reporting alternatives

of management information systems

 Describe how online analytical processing

can meet key information needs of managers

 Explain the decision support system concept

and how it differs from traditional management
information systems
9-2
 Learning Objectives

 Explain how these information systems can

support the information needs of executives,
managers, and business professionals
– Executive information systems
– Enterprise information portals
– Knowledge management systems

9-3
 Learning Objectives

 Identify how neural networks, fuzzy logic,

genetic algorithms, virtual reality, and
intelligent agents can be used in business
 Give examples of ways expert systems
can be used in business decision-making
situations

9-4
 Decision Support in Business

Companies
Companies invest
invest
in
in data-driven
data-driven Changing marketing conditions
decision
decision support
support
application
application Customer needs
frameworks
frameworks to to help
help
them
them respond
respond toto
Management information
Accomplished
Accomplished by by Decision support
several
several types
types of
of
Other information systems

9-5
 Case 1: Hillman Group, Avnet, Quaker Chemical

 BI refers to a variety of software applications used to

analyze an organization’s raw data and extract useful
insights from them
 BI tools, coupled with business process changes, can
have a significant impact on the bottom line
 Most companies don’t understand their business
processes well enough to determine how to improve
them
 Companies using BI to uncover flawed business
processes can more successfully compete against
companies using BI merely to monitor what’s happening

9-6
 Case Questions

 What are the business benefits of BI

deployments such as those implemented by
Avnet and Quaker Chemical?
– What roles do data and business processes
play in achieving those benefits?
 What are the main challenges to the change of
mindset required to extend BI tools beyond mere
reporting?
– What can companies do to overcome them?

9-7
 Case Questions

 Avnet and Quaker Chemical implemented

systems and processes that affect the practices
of their salespeople
– In which ways did the latter benefit from these
new implementations?
– How important was their buy-in to the success
of these projects?
– Discuss alternative strategies for companies to
foster adoption of new systems like these

9-8
Levels of Managerial Decision Making

9-9
 Information Quality

Information products are made more valuable

by their attributes, characteristics, or qualities
Outdated, inaccurate, or hard to understand
information has much less value

Information has three dimensions

Time Content Form

9-10
Attributes of Information Quality

9-11
 Decision Structure

Structured The procedures to follow when a

(operational) decision is needed can be
specified in advance

Unstructured It is not possible to specify in

(strategic) advance most of the decision
procedures to follow

Semi-structured Decision procedures can be

(tactical) pre-specified, but not enough to
lead to the correct decision

9-12
 Decision Support Systems

Management Information Decision Support Systems

Systems

Decision Provide information about Provide information and

support the performance of the techniques to analyze
provided organization specific problems

Information Periodic, exception, demand, Interactive inquiries and

form and and push reports and responses
frequency responses

Information Pre-specified, fixed format Ad hoc, flexible, and

format adaptable format

Information Information produced by Information produced by

processing extraction and manipulation analytical modeling
methodology of business data of business data

9-13
 Decision Support Trends

Personalized
Information
decision Modeling
retrieval
support

Data What-if
Reporting
warehousing scenarios

9-14
Decision Support Trends

9-15
Business Intelligence Applications

9-16
 Decision Support Systems

 To support the making of semi-structured

business decisions, DSS uses
– Analytical models
– Specialized databases
– Decision-maker’s own insights and judgments
– Interactive, computer-based modeling process
 DS systems
– Ad hoc, quick-response systems
– Initiated and controlled by decision makers

9-17
DSS Components

9-18
 DSS Model Base

 Model Base
– A software component
– Consists of models used in computational
and analytical routines
– Mathematically expresses relationships
among variables
 Spreadsheet Examples
– Linear programming
– Multiple regression forecasting
– Capital budgeting present value

9-19
Applications of Statistics and Modeling

Simulate & optimize supply chain

Supply Chain
flows, reduce inventory & stock-outs

Identify the price that maximizes

Pricing
yield or profit

Product & Service Detect quality problems early in

Quality order to minimize them

Research & Improve quality, efficacy, and safety

Development of products and services

9-20
Management Information Systems

The original type of information system

that supported managerial decision making

Produces information products that support

many day-to-day decision-making needs

Produces reports, displays, and responses

Satisfies needs of operational and tactical

decision makers who face structured decisions

9-21
 Management Reporting Alternatives

Periodic Scheduled Pre-specified format, issued

Reports on a regular basis

Reports about exceptional

Exception Reports
conditions, scheduled or on event

Demand Reports &

Information is available on demand
Responses

Information is pushed to a
Push Reporting
networked computer

9-22
 Online Analytical Processing

 OLAP
– Enables managers and analysts to examine
and manipulate large amounts of detailed and
consolidated data from many perspectives
– Done interactively, in real time, with rapid
response to queries

9-23
 Online Analytical Operations

Consolidation
Aggregation of data
Ex: sales office data, rolled up to the district level

Drill-Down
Display underlying detail data
Ex: sales figures by individual product

Slicing and Dicing

Viewing database from different viewpoints
Often performed along a time axis
9-24
Geographic Information Systems (GIS)

DSS uses geographic databases to construct

and display maps and other graphic displays

Supports decisions affecting the geographic

distribution of people and other resources

Often used with Global Positioning

System (GPS) devices

9-25
Data Visualization Systems (DVS)

Represents complex data using interactive, three-

dimensional graphical forms (charts, graphs, maps)

Helps users interactively sort, subdivide, combine,

and organize data while it is in its graphical form

9-26
 Using Decision Support Systems

 Using a decision support system involves

an interactive analytical modeling process
– Decision makers are not demanding
pre-specified information
– They are exploring possible alternatives

9-27
Using Decision Support Systems

What-If
What-If Sensitivity
Sensitivity
Analysis
Analysis Analysis
Analysis

Basic analytical modeling activities

Goal-seeking
Goal-seeking Optimization
Optimization
Analysis
Analysis Analysis
Analysis

9-28
 Data Mining

 Decision support through knowledge discovery

– Analyzes vast stores of historical business data
– Looks for patterns, trends, and correlations
– Goal is to improve business performance

 Types of analysis
– Regression
– Decision tree
– Neural network
– Cluster detection
– Market basket analysis

9-29
Analysis of Customer Demographics

9-30
 Market Basket Analysis

 One of the most common uses for data mining

– Determines what products customers purchase
together with other products
 Typical applications of MBA
– Cross-selling
– Product placement
– Affinity promotion
– Survey analysis
– Fraud detection
– Customer behavior identification

9-31
Executive Information Systems (EIS)

Combines many Provides top executives

features of with immediate, easy
MIS and DSS access to information

Identifies factors So popular it was

critical to expanded to managers,
accomplishing analysis, and other
strategic objectives knowledge workers

9-32
 Features of an EIS

 Information presented in forms tailored to

the preferences of the executives using
the system
– Customizable graphical user interfaces
– Exception reports
– Trend analysis
– Drill down capability

9-33
Web-Based Executive Information System

9-34
 Enterprise Information Portals

 A Web-based interface and integration of

MIS, DSS, EIS, and other technologies
– Available to all intranet users and select
extranet users
– Provides access to a variety of internal and
external business applications and services
– Typically tailored or personalized to the user
or groups of users
– Often has a digital dashboard
– Also called enterprise knowledge portals

9-35
Enterprise Information Portal Components

9-36
Enterprise Knowledge Portal

9-37
Case 2: Goodyear, JEA, OSUMC, Monsanto

 Advanced technologies (AI, mathematical simulations,

robotics) can have dramatic impacts on business processes
and financial results
– Goodyear designers can perform tests 10 times faster using
simulation, reducing a new tire’s time to market from two
years to nine months
– Public Utility Company JEA uses neural network technology
to automatically determine the optimal combinations of oil
and natural gas the utility’s boilers need to produce electricity
cost effectively, given fuel prices and the amount of electricity
required
– The Ohio State University Medical Center replaced its
overhead rail transport system with 46 self-guided robotic
vehicles to move linens, meals, trash, and medical supplies
throughout the 1,000-bed hospital
9-38
 Case Study Questions

 In all of the project outcomes in the case, the payoffs

are both larger and achieved more rapidly than in more
traditional system implementations
– Why do you think this is the case?
– How are these projects different from others you
have come across in the past?
– What are those differences?
 How do these technologies create business value for
the implementing organizations?
– In which ways are these implementations similar in
how they accomplish this, and how are they different?

9-39
 Case Study Questions

 In all of the case examples, companies had an

urgent need that prompted them to investigate
radical, new technologies
– Do you think the story would have been different
had the companies been performing well
already? Why or why not?
– To what extent are these innovations dependent
on the presence of a problem or crisis?

9-40
 Artificial Intelligence (AI)

Computer
Engineering
science
AI is
a field of science
Mathematics and technology Biology
based on…

Linguistics Psychology

9-41
 Artificial Intelligence (AI)

Think

Feel See
Ultimate
goal for
computers

Talk Hear

Walk

9-42
 Attributes of Intelligent Behavior

Learn or
Use reason to
Think and reason understand from
solve problems
experience

Deal with complex

Acquire and apply Exhibit creativity
or perplexing
knowledge and imagination
situations

Recognize Handle
Respond quickly
relative ambiguous,
and successfully
importance of incomplete,
to new situations
situation elements erroneous info

9-43
Domains of Artificial Intelligence

9-44
 Expert Systems

An Expert System (ES)

Knowledge-based information system

Contains knowledge about a

specific, complex application area

Acts as an export consultant to end users

9-45
Components of an Expert System

9-46
Methods of Knowledge Representation

Case-based
Frame-based
Object-based
Rule-based

9-47
Expert System Application Categories

Decision Management

Diagnostic/Troubleshooting

Design/Configuration

Selection/Classification

Process Monitoring/Control

9-48
 Benefits of Expert Systems

Captures expertise of expert(s) in a

computer-based information system

Faster and more consistent than an expert

Can contain knowledge of multiple experts

Does not get tired or distracted

Cannot be overworked or stressed

Helps preserve and reproduce the
knowledge of human experts

9-49
 Limitations of Expert Systems

 Major limitations of expert systems

– Limited focus
– Inability to learn
– Maintenance problems
– Development and maintenance costs
– Can only solve specific types of problems
in a limited domain of knowledge

9-50
 Developing Expert Systems

Suitability Criteria for Expert Systems

Domain
Domain Expertise
Expertise Complexity
Complexity
Thedomain
The domainor
or Solutionsto
Solutions tothe
the Problem
Problem
subjectarea
subject areaof
of problemrequire
problem require solvingisis
solving
theproblem
the problemisis theefforts
the effortsof
ofan
an complex,and
complex, and
smalland
small andwell-
well- expert
expert requireslogical
requires logical
defined
defined inference
inference
processing
processing

9-51
 Developing Expert Systems

Suitability Criteria for Expert Systems

Structure… solution process must be able

to cope with ill-structured, uncertain, missing, and
conflicting data and a changing problem situation

Availability… an expert exists who is articulate,

cooperative, and supported by the management
and end users involved in the development process

9-52
 Development Tool

 Expert System Shell

– The easiest way to develop an expert system
– A software package consisting of an expert
system without its knowledge base
– Has an inference engine and user interface
programs

9-53
 Knowledge Engineering

 A knowledge engineer
– Works with experts to capture the knowledge
(facts and rules of thumb) they possess
– Builds the knowledge base, and if necessary,
the rest of the expert system
– Performs a role similar to that of systems
analysts in conventional information systems
development

9-54
 Neural Networks

 Computing systems modeled after the brain’s

mesh-like network of interconnected processing
elements (neurons)
– Interconnected processors operate in parallel
and interact with each other
– Allows the network to learn from the data it processes
– Recognizes patterns and relationships in data
9-55
 Fuzzy Logic

Resembles human reasoning

Allows approximate values and inferences,
and incomplete or ambiguous data
Uses terms like “very high” instead of precise measures

Allows processing of incomplete data

Results in quick, approximate solutions

Used in fuzzy process controllers
(subway trains, elevators, cars)

9-56
Example of Fuzzy Logic Rules and Query

9-57
 Genetic Algorithms

Uses
Uses Darwinian,
Darwinian, Stimulates
Stimulates anan
randomizing,
randomizing, and
and evolutionary
evolutionary process,
process,
other
other mathematical
mathematical yielding
yielding increasingly
increasingly
functions
functions better
better solutions
solutions

Genetic algorithm software

Especially
Especially useful
useful for
for Being
Being used
used to
to model
model aa
situations
situations in
in which
which variety
variety of
of scientific,
scientific,
thousands
thousands ofof solutions
solutions technical,
technical, and
and business
business
are
are possible
possible processes
processes

9-58
 Virtual Reality (VR)

 Virtual reality is a computer-simulated reality

– Fast-growing area of artificial intelligence
– Originated from efforts to build natural,
realistic, multi-sensory human-computer
interfaces
– Relies on multi-sensory input/output devices
– Creates a three-dimensional world through
sight, sound, and touch
– Also called telepresence

9-59
 Typical VR Applications

Computer-aided Medical diagnostics

design and treatment

Scientific
Entertainment
Current
Current experimentation
applications
applications
of
of virtual
virtual reality
reality
Employee Flight
training simulation

Product
demonstrations

9-60
 Intelligent Agents

Software surrogate for an end user or a

process that fulfills a stated need or activity

Uses built-in and learned knowledge base to make

decisions and accomplish tasks in a way
that fulfills the intentions of a user

Also called software robots or bots

9-61
 User Interface Agents

Observe user computer operations, correct

Interface
user mistakes, provide hints/advice on
Tutors
efficient software use

Presentation Show information in a variety of

Agents forms/media based on user preferences

Network Discover paths to information, provide ways

Navigation
Agents to view it based on user preferences
Play what-if games and other roles to help
Role
users understand information and make
Playing
better decisions

9-62
 Information Management Agents

Help users find files and databases, search

Search for information, and suggest and find new
Agents types of information products, media,
resources

Provide commercial services to discover and

Information
develop information resources that fit
Brokers
business or personal needs

Receive, find, filter, discard, save, forward,

Information and notify users about products received or
Filters desired, including e-mail, voice mail, and
other information media

9-63
Case 3: Harrah’s, LendingTree, DeepGreen, Cisco

 The promise of AI of automating decision

making has been very slow to materialize
 The new generation AI applications
– Easier to create and manage
– Don’t require anyone to identify problems
or to initiate analysis
– Decision-making capabilities are embedded
into the normal flow of work, and are triggered
without human intervention

9-64
Case 4: Harrah’s, LendingTree, DeepGreen, Cisco

 The new generation AI applications

– Sense online data or conditions, apply codified
knowledge or logic and make decisions with
minimal human intervention
– Rely on experts and managers to create
and maintain rules and monitor the results
– Managers in charge of automated decision
systems must develop processes for
managing exceptions

9-65
 Case Study Questions

 Why did some previous attempts to use

artificial intelligence technologies fail?
– What differences between the new AI-based
applications versus the old caused the
authors to declare that automated decision
making is finally coming of age?
 What types of decisions are best suited for
automated decision making?
– Provide examples of successful applications
from the companies in this case
9-66
 Case Study Questions

 What role do humans play in automated

decision making applications?
– What challenges face managers where
automated decision-making systems are
being used?
– What solutions are needed to meet such
challenges?

9-67