Transcript Ch07_final - People Search

MANAGING
INFORMATION
TECHNOLOGY
FIFTH EDITION
CHAPTER 7
MANAGERIAL SUPPORT SYSTEMS
E. Wainright Martin  Carol V. Brown  Daniel W. DeHayes
Jeffrey A. Hoffer  William C. Perkins
DECISION SUPPORT SYSTEMS
 Designed to assist decision
makers with unstructured
problems
 Usually interactive
 Incorporates data and
models
 Data often comes from
transaction processing
systems or data warehouse
© 2005 Pearson Prentice-Hall
Chapter 7 - 2
Page 212
DECISION SUPPORT SYSTEMS
Three major components
© 2005 Pearson Prentice-Hall
Chapter 7 - 3
Figure 7.1 Decision Support Systems
Components
Page 213
DECISION SUPPORT SYSTEMS
 Specific DSSs – actual DSS applications that
directly assist in decision making
 DSS generator – a software package used to
build a specific DSS quickly and easily

Examples: Microsoft Excel or Lotus 1-2-3
DSS model 1
used to create
DSS generator
DSS model 2
DSS model 3
© 2005 Pearson Prentice-Hall
Chapter 7 - 4
Page 212
How Big is an Exabyte?
Kilobyte (KB) = 10 3
= 1,000 bytes
2 KB: a written page
Megabyte (MB) = 10 6
= 1,000,000 bytes
1 MB: a small novel
Gigabyte (GB) = 10 9
= 1,000,000,000 bytes
1 GB: a pickup truck filled with books
20 GB: a good collection of the works of
Beethoven
Terabyte (TB) = 10 12
= 1,000,000,000,000 bytes
2 TB: an academic research library
10 TB: the printed collections of the U.S.
Library of Congress
Petabyte (PB) = 10
= 1,000,000,000,000,000 bytes
20 PB: production of hard-disk drives in
1995
200 PB: all printed material
Exabyte (EB) = 10 18
= 1,000,000,000,000,000,000
bytes
2 EB: total volume of information generated
in 1999
15
Business Intelligence
Reporting tools
 Reporting tools are programs that read data from a
variety of sources, process that data, produce formatted
reports, and deliver those reports to the users who need
them.
 Reporting tools are used primarily for assessment to
address questions like:
 What has happened in the past?
 What is the current situation?
 How does the current situation compare to the
past?
 Reporting tools use simple operations like sorting,
grouping, and summing.
Business Intelligence
Data-mining tools
 Data-mining tools process data using statistical
techniques, many of which are sophisticated.
 Data mining involves searching for patterns and
relationships among data.
 In most cases, data-mining tools are used to make
predictions. For example,

We can use one form of analysis to compute
the probability that a customer will default on a
loan.
Trade Data for NDX.X (NASDAQ 100)
Report based on Trade Data
Components of a Reporting System
Report Characteristics
RFM Analysis
 RFM analysis is a way of analyzing and ranking
customers according to their purchasing patterns.
 It considers how recently (R) a customer has ordered,
how frequently (F) a customer orders, and how much
money (M) the customer spends per order.
 To produce an RFM score, the program first sorts
customer purchase records by the date of their most
recent (R) purchase. The top 20% of the customers
having the most recent orders are given an R score 1
(highest).
 The program then re-sorts the customers on the basis of
how frequently they order.
 Finally the program sorts the customers again according
to the amount spent on their orders.
Example of RFM Score Data
Online Analytical Processing (OLAP)
 OLAP provides the ability to sum, count, average, &
perform other simple arithmetic operations on groups of
data.
 The viewer of the report can change the report’s format,
hence, the term online.
 An OLAP report has measures and dimensions. A
measure is the data item of interest. The item is to be
summed or averaged or otherwise processed in the OLAP
report.
 A dimension is a characteristic of a measure. Examples
are purchase data, customer type, customer location, and
sales region
OLAP Product Family & Store Location by Store Type
Data Warehouses and Data Marts
 Basic reports and simple OLAP analyses can be
made directly from operational data.
 For the most part, such reports display the current
state of the business; and if there are a few
missing values or small inconsistencies with the
data, no one is too concerned.
 Operational data are unsuited to more
sophisticated analyses, particularly, data-mining
analyses that require high-quality input for
accurate and useful results.
Data Warehouses and Data Marts
 Many organizations choose to extract operational
data into facilities called data warehouses and data
marts for data mining and other analyses.
 Programs read operational data and extract, clean,
and prepare that data for business intelligence
processing.
 Data warehouses include data that are purchased
from outside sources.
 The data-warehouse DBMS extracts and provides
data to business intelligence tools such as datamining programs.
Components of a Data Warehouse
Problems of Using Transaction Data
for Analysis and Data Mining
Data Mart Examples
Data Mining
 Data mining is the application of statistical techniques to
find patterns and relationships among data and to classify
and predict.
 With unsupervised data mining, analysts do not create a
model or hypothesis before running the analysis.
 A common use for cluster analysis is to find groups of
similar customers from customer order and
demographic data.
 With supervised data mining, data miners develop a
model prior to the analysis and apply statistical techniques
to data to estimate parameters of the model. One such
analysis is called a regression analysis.
Market-Basket Analysis
 A market-basket analysis is a data-mining
technique for determining sales patterns.
 A market-basket analysis shows the products
that customers tend to buy together.
 You can expect market-basket analysis to
become a standard CRM analysis during your
career.
Decision Trees
 A decision tree is a hierarchical arrangement of
criteria that predict a classification or a value.
 Decision tree analyses are an unsupervised datamining technique.
 The analyst sets up the computer program and
provides the data to analyze, and the decision tree
program produces the tree.
 A common business application of decision trees is to
classify loans by likelihood of default.
 Organizations analyze data from past loans to
produce a decision tree that can be converted to
loan-decision rules.
DATA MINING
Data Mining – uses different technologies to
search for (mine) “nuggets” of information
from data stored in a data warehouse
 Data
mining software:
 Oracle 9i Data Mining and Oracle Data Mining Suite
 SAS Enterprise Miner
 IBM Intelligent Miner Modeling
 Angoss Software’s KnowledgeSEEKER, Knowledge Studio,
and KnowledgeExcelerator
 Datamation’s Data Mining and Business Intelligence Product
© 2005 Pearson Prentice-Hall
Chapter 7 - 24
Page 215
DATA MINING
Data Mining – uses different technologies to
search for (mine) “nuggets” of information
from data stored in a data warehouse

Decision techniques used:
Decision trees
Linear and logistic regression
Clustering for market segmentation
Rule induction
Nearest neighbor
Genetic algorithms
© 2005 Pearson Prentice-Hall
Chapter 7 - 25
Page 215
DATA MINING
 Uses:
Cross-selling
 Customer churn
 Customer retention
 Direct marketing
 Fraud detection
 Interactive marketing
 Market basket analysis
 Market segmentation
 Payment or default analysis
 Trend analysis

© 2005 Pearson Prentice-Hall
Chapter 7 - 26
see Table 7.1 Uses of Data Mining
Page 216
GROUP SUPPORT SYSTEMS
 Type of DSS to support a group rather than an
individual
 Specialized type of groupware
 Attempt to make group meetings more
productive
 Now focus on supporting team in all its
endeavors, including “different time, different
place” mode – virtual teams
© 2005 Pearson Prentice-Hall
Chapter 7 - 27
Page 217-218
GROUP SUPPORT SYSTEMS
Traditional “same time, same place” meeting layout
© 2005 Pearson Prentice-Hall
Chapter 7 - 28
Figure 7.2 Group Support System Layout
Page 217
GEOGRAPHIC INFORMATION
SYSTEMS
GISs – systems based on manipulation of
relationships in space that use geographic
data
 Early
GIS users:
Natural resource management
Public administration
NASA and the military
Urban planning
Forestry
Map makers
© 2005 Pearson Prentice-Hall
Chapter 7 - 29
Page 219
GEOGRAPHIC INFORMATION
SYSTEMS
Business Adopts Geographic Technologies
 Business
uses:
Determining site locations
Market analysis and planning
Logistics and routing
Environmental engineering
Geographic pattern analysis
© 2005 Pearson Prentice-Hall
Chapter 7 - 30
Page 219
(Reprinted courtesy of Environmental Systems Research Institute, Inc. Copyright © 2003 Environmental Systems Research
Institute, Inc. All rights reserved.)
© 2005 Pearson Prentice-Hall
Chapter 7 - 31
Figure 7.3 Department Store Analysis
Page 219
GEOGRAPHIC INFORMATION
SYSTEMS
What’s Behind Geographic Technologies
 Approaches to representing spatial data:

Raster-based GISs – rely on dividing space into
small, uniform cells (rasters) in a grid

Vector-based GISs – associate features in the
landscape with a point, line, or polygon

Geodatabase model – uses object-oriented data
concepts
© 2005 Pearson Prentice-Hall
Chapter 7 - 32
Page 220
GEOGRAPHIC INFORMATION
SYSTEMS
Coverage model uses
different layers to represent
similar types of geographic
features in the same area
© 2005 Pearson Prentice-Hall
Chapter 7 - 33
Figure 7.4 Map Layers in a GIS
Page 221
GEOGRAPHIC INFORMATION
SYSTEMS
What’s Behind Geographic Technologies
 Questions geographic analysis can answer:

What is adjacent to this feature?

Which site is the nearest one?

What is contained within this area?

Which features does this element cross?

How many features are within a certain distance
of a site?
© 2005 Pearson Prentice-Hall
Chapter 7 - 34
Page 221
EXECUTIVE INFORMATION
SYSTEMS/BUSINESS INTELLIGENCE
SYSTEMS
EISs – a hands-on tool that focuses, filters, and organizes
an executive’s information so he or she can make more
effective use of it
Where does EIS data come from?
 Filtered and summarized transaction data (internal)
 Collected competitive information (internal and external)
© 2005 Pearson Prentice-Hall
Chapter 7 - 35
Page 222-223
EXECUTIVE INFORMATION
SYSTEMS/BUSINESS INTELLIGENCE
SYSTEMS
 Executive information system (EIS):

Delivers online current information about
business conditions in aggregate form

Easily accessible to senior executives and
other managers

Designed to be used without intermediary
assistance

Uses state-of-the-art graphics,
communications and data storage methods
© 2005 Pearson Prentice-Hall
Chapter 7 - 36
Page 222-223
(Courtesy of Geac Computer Corporation Limited. Copyright © 2003 Geac Computer Corporation Limited.)
© 2005 Pearson Prentice-Hall
Chapter 7 - 37
Figure 7.5 Example Geac Performance
Management Displays
Page 225
(Courtesy of Geac Computer Corporation Limited. Copyright © 2003 Geac Computer Corporation Limited.)
© 2005 Pearson Prentice-Hall
Chapter 7 - 38
Figure 7.5 Example Geac Performance
Management Displays
Page 225
KNOWLEDGE MANAGEMENT
SYSTEMS
 Knowledge management (KM):

Set of practical and action-oriented management
practices

Involves strategies and processes of identifying,
creating, capturing, organizing, transferring, and
leveraging knowledge to help compete

Relies on recognizing knowledge held by
individuals and the firm
© 2005 Pearson Prentice-Hall
Chapter 7 - 39
Page 226
KNOWLEDGE MANAGEMENT
SYSTEMS
 Knowledge management system (KMS):

System for managing organizational knowledge

Technology or vehicle that facilitates the sharing
and transferring of knowledge so that valuable
knowledge can be reused

Enable people and organizations to enhance
learning, improve performance, and produce longterm competitive advantage
© 2005 Pearson Prentice-Hall
Chapter 7 - 40
Page 226
ARTIFICIAL INTELLIGENCE
AI – the study of how to make computers
do things that are currently done better by
people
 Six areas:






© 2005 Pearson Prentice-Hall
Natural languages
Robotics
Perceptive systems
Genetic programming
Expert systems
Neural networks
Chapter 7 - 41
Page 229
ARTIFICIAL INTELLIGENCE
AI – the study of how to make computers
do things that are currently done better by
people
 Six areas:






© 2005 Pearson Prentice-Hall
Natural languages
Robotics
Perceptive systems
Genetic programming
Expert systems
Neural networks
Chapter 7 - 42
Most relevant for
managerial support
Page 229
EXPERT SYSTEMS
Expert systems – attempt to capture the
expertise of humans in a computer program
 Knowledge engineer:

A specially trained systems analyst who works
closely with one or more experts in the area of
study

Tries to learn about how experts make decisions

Loads information (what learned) into module
called knowledge base
© 2005 Pearson Prentice-Hall
Chapter 7 - 43
Page 229
EXPERT SYSTEMS
© 2005 Pearson Prentice-Hall
Chapter 7 - 44
Figure 7.6 Architecture of an Expert System
Page 229
EXPERT SYSTEMS
Obtaining an Expert System
 Approaches:
 Buy
a fully developed system created
for a specific application
 Develop
using a purchased expert
system shell (basic framework) and
user-friendly special language
 Have
knowledge engineers custom
build using special-purpose language
(such as Prolog or Lisp)
© 2005 Pearson Prentice-Hall
Chapter 7 - 45
Page 230
EXPERT SYSTEMS
Examples of Expert Systems

Standford University’s MYCIN – to diagnose and
prescribe treatment for meningitis and blood diseases

General Electric’s CATS-1 to diagnose mechanical
problems in diesel locomotives

AT&T’s ACE to locate faults in telephone cables

Market Surveillance software – to detect insider trading

FAST software – for credit analysis, used by banking
industry

Nestle Food’s developed system to provide employees
information on pension fund status
© 2005 Pearson Prentice-Hall
Chapter 7 - 46
Page 230
NEURAL NETWORKS
Neural networks – attempt to tease out meaningful patterns
from vast amounts of data
 Process:
1.
2.
3.
4.
5.
6.
Program given set of data
Program analyzed data, works out correlations, selects
variables to create patterns
Pattern used to predict outcomes, then results
compared to known results
Program changes pattern by adjusting variable weights
or variables themselves
Repeats process over and over to adjust pattern
When no further adjustment possible, ready to be used
to make predictions for future cases
© 2005 Pearson Prentice-Hall
Chapter 7 - 47
Page 232
NEURAL NETWORKS
© 2005 Pearson Prentice-Hall
Chapter 7 - 48
Table 7.2 Uses of Neural Networks
Page 232
VIRTUAL REALITY
Virtual reality – use of a computer-based system to create
an environment that seems real to one or more senses of
users
 Non-entertainment categories:



Training
Design
Marketing
© 2005 Pearson Prentice-Hall
Chapter 7 - 49
Page 233
VIRTUAL REALITY
Training
U.S. Army to train tank crews
Amoco for training its drivers
Duracell for training factory workers on using new
equipment
Design
Design of automobiles
Walk-throughs of air conditioning/ furnace units
Marketing
Interactive 3-D images of products (used on the Web)
Virtual tours used by real estate companies or resort hotels
© 2005 Pearson Prentice-Hall
Chapter 7 - 50
Page 234-235
VIRTUAL REALITY
Training
U.S. Army to train tank crews
Amoco for training its drivers
Duracell for training factory workers on using new
equipment
Design
Design of automobiles
Walk-throughs of air conditioning/ furnace units
Marketing
Interactive 3-D images of products (used on the Web)
Virtual tours used by real estate companies or resort hotels
© 2005 Pearson Prentice-Hall
Chapter 7 - 51
Page 234-235
VIRTUAL REALITY
(Courtesy of Homestore, Inc. Copyright © 2004 Homestore, Inc.)
© 2005 Pearson Prentice-Hall
Chapter 7 - 52
Figure 7.7 Hometour 360o Virtual Tour
of Living Room
Page 235