Decision Support, Knowledge Management and Expert Systems

1
Decision Support, Knowledge Management and Expert
Systems

• Brian Mennecke

2
How can IT be used to support decision makers?

• By supporting various individual and team
  activities and roles
• Communication and team interaction
• The assimilation and filtering of data
• Assist with problem recognition
• Assist with problem solving
• Putting together the results into a cohesive
  package

3
Data is turned into information, but the decision
maker also needs Knowledge to make decisions

• Types of knowledge
• Descriptive Knowledge
• Procedural Knowledge
• Reasoning Knowledge
• Forms of Knowledge
• Tacit Knowledge
• Explicit Knowledge

4
(No Transcript)
5
(No Transcript)
6
Examples of technologies that can support or
enhance the transformation of knowledge (IBM
Systems Journal)
7
Knowledge Management Tools

• Text and Forms management
• Database and Reporting management
• Spreadsheet, Solvers and Charts management
• Programming management.
• Rules management

8
Decision Support Systems (DSS)

• DSS can be classified as
• data-oriented
• provide tools for the manipulation and analysis
  of data
• model-based
• generally have some kind of mathematical model of
  the decision being supported

9
A model of a DSS
10
A model of a Spatial DSS
11
So, how does a DSS benefit decision makers

• Supplements the decision maker
• Allows improved intelligence, decision, and
  choice activities
• Facilitates problem solving
• Provides assistance with non-structures decisions
• Assists with knowledge management

12
Information Requirements by Management Level
13
Structured vs. Semi-Structured

• For each decision you make, the decision will
  fall into one of the following categories
• Structured Decisions
• Unstructured
• Semi-Structured

14
Structured Decisions

• Often called programmed decisions because they
  are routine and there are usually specific
  policies, procedures, or actions that can be
  identified to help make the decision
• This is how we usually solve this type of
  problem

15
Unstructured Decisions

• Decision scenarios that often involve new or
  unique problems and the individual has little or
  no programmatic or routine procedure for
  addressing the problem or making a decision

16
Semi-structured Decisions

• Decision scenarios that have some structured
  components and some unstructured components.

17
DSS Examples

• American Airlines Yield Management
• maximizes the revenue or yield from each flight
  through overbooking, discount seats, and traffic
  management
• resulted in total quantifiable benefits of more
  than 1.4 billion for AA
• Pfizer distribution system
• supports decisions about the US distribution
  network for distributing finished goods,
  including warehousing, transportation and
  ultimate delivery to the customer
• Merrill Lynchs Integrated Choice Account
  Structure
• helped design appropriate account structures and
  pricing for the company Integrated Choice program
• analysis considered the total revenue at risk,
  estimated what accounts customers would choose,
  and the impact of their choice on revenues
• Helped the company increase assets and customers

18
The Role of the Decision Maker

• Decision makers can be
• Individuals
• Teams
• Groups
• Organizations
• All of these types of decision makers will differ
  in their knowledge and experience therefore,
  there will be differences in how they will react
  to a given problem scenario

19
The Decision Making Process

• Regardless of the type of decision maker, all
  decisions involve the following steps
• Intelligence
• Design
• Choice
• Decision
• Implementation

20
Strategies for Making Decisions

• Optimization
• Satisficing
• Elimination by Aspects
• Incrementalism
• Mixed Scanning
• Analytic Hierarchy Process

21
Types of Models

• Deterministic linear programming and production
  planning
• Stochastic queuing theory and regression
  analysis
• Simulation transportation analysis and
  production modeling
• Domain-specific meteorological models, geologic
  models, economic models

22
Conceptual Models

• Formal approaches are not always feasible
• Most all problem is always completely new
• Decision makers can therefore recall and combine
  a variety of past experiences to create a model
  of the current situation
• The Garbage can approach to decision making

23
Spatial DSS A Geographic Information System

• A geographic information system (GIS) is a
  computer-based information system that provides
  tools to collect, integrate, manage, analyze,
  model, and display data that is referenced to an
  accurate cartographic representation of objects
  in space. (Mennecke, Dangermond, Santoro,
  Darling, Crossland, 1995).

24
Location Based Services

• Location-based services incorporate information
  about the user's location into the provision of
  products or services. These include
• Locator services (e.g., wheres the closest ATM?)
• Navigation systems (e.g., in the car or on your
  PC)
• M-commerce applications (e.g., proximity alerts,
  closest service, mobile advertizing)

25
GIS Examples

• Online
• www.MapQuest.com
• Maps.google.com
• Desktop
• ArcGIS by ESRI
• MS MapPoint

26
Expert Systems

• An expert system acts or behaves like a human
  expert in a field or area.

27
Expert Systems

• Advisory programs that attempt to imitate the
  reasoning process of human experts
• Reasons to build Expert Systems
• to make the expertise of an individual available
  to others in the field
• to capture knowledge from an expert who is likely
  to be unavailable in the future
• to provide consistency in decision making

28
Characteristics of Human Experts

• Recognize and Formulate the problem
• Solve the problem relatively quickly
• Explain the solution and rationale
• Learn from experience
• Restructure knowledge
• Break the rules when necessary
• Determine relevance

29
Components of an Expert System

• An expert system consists of a collection of
  integrated and related components, including
• Knowledge Base
• An Inference Engine
• Explanation Facility
• Knowledge Acquisition Subsystem
• A User Interface.

30
The Knowledge Base

• The knowledge base stores all relevant
  information, data, rules, cases, and
  relationships used by the expert system.
• A knowledge base must assemble the knowledge of
  multiple human experts.

31
The Knowledge Base

• Fuzzy logic - entails dealing with ambiguous
  criteria or probabilities and events that are not
  mutually exclusive.
• A semantic network is a collection of items or
  nodes linked together to show the relationship
  between items in the knowledge base.

32
The Knowledge Base

• A rule is a conditional statement that links
  given conditions to actions or outcomes.
• A frame is another approach used to capture and
  store knowledge in a knowledge base. It relates
  an object or item to various facts or values.
• An expert system can use cases in developing a
  solution to the current problem or situation.

33
The Inference Engine

• The purpose of the inference engine is to seek
  information and relationships from the knowledge
  base and to provide answers, predictions, and
  suggestions the way a human expert would.
• The inference engine must find the right facts,
  interpretations, and rules and assemble them
  correctly.

34
The Inference Engine

• Forward chaining starts with the facts and works
  forward to the conclusions.
• Backward chaining is the process of starting with
  conclusions and working backward to the
  supporting facts.

35
(No Transcript)
36
The Explanation Facility

• The explanation facility allows a user or
  decision maker to understand how the expert
  system arrived at certain conclusions or results.

37
The Knowledge Acquisition Facility

• The overall purpose of the knowledge acquisition
  facility is to provide a convenient and efficient
  means for capturing and storing all components of
  the knowledge base.

38
The User Interface

• Specialized user interface software is used for
  designing, creating, updating, and using expert
  systems. The overall purpose of the user
  interface is to make the development and use of
  an expert system easier for users and decision
  makers.

39
Characteristics of Expert Systems

• Expert systems have the ability to
• Explain their reasoning or suggested decisions.
• Display intelligent behavior.
• Manipulate symbolic information and draw
  conclusions.
• Draw conclusions from complex relationships.
• Provide portable knowledge.
• Can deal with uncertainty.

40
Capabilities of Expert Systems

• Expert systems offer a number of powerful
  capabilities and benefits.
• Some capabilities of expert systems include
• Superior problem solving.
• Ability to save and apply knowledge and
  experience to problems.

41
Capabilities of Expert Systems

• Reduced response time for complex problems.
• The ability to look at problems from a variety of
  perspectives.
• Expert systems can be used to solve problems in
  every field or discipline, and can assist in all
  stages of problem-solving.

42
Benefits of Expert Systems

• Increased Output and Productivity
• Increased Quality
• Reduced Downtime
• Captures Scarce Expertise
• Flexibility
• Equipment Operation
• Knowledge Transfer to Remote Locations

• Reliability
• Response Time
• Integration of Several Expert Opinions
• Operation in Hazardous Environments
• Incomplete Information
• Educational Benefits

43
Limiting Characteristics of Expert Systems

• Possibility of error.
• Cannot refine own knowledge base.
• Difficult to maintain.
• May have high development costs.
• Raise legal and ethical concerns.
• Expertise is hard to extract
• Expert Vocabulary and Jargon
• Requires a Knowledge Engineer
• Experts do not perform well under pressure

44
Uses of Expert Systems

• Strategic goal setting
• Planning
• Design
• Scheduling
• Monitoring
• Diagnosis

• Debugging
• Repair
• Instruction
• Control
• Prediction
• Interpretation

45
When to Use Expert Systems

• Factors that make expert systems worth the high
  cost
• A high potential payoff or significantly reduced
  downside risk.
• The ability to capture and preserve irreplaceable
  human experience.
• The ability to develop a system more consistent
  than human experts.

46
When to Use Expert Systems

• Expertise needed at a number of locations at the
  same time.
• Expertise needed in a hostile environment that is
  dangerous to human health.
• The expert system solution can be developed
  faster than the solution from human experts.
• Expertise needed for training and development so
  as to share the wisdom and experience of human
  experts with many people.

47
Expert Systems Development

• Steps in the expert systems development process
  include
• Determining requirements.
• Identifying experts.
• Constructing expert system components.
• Implementing results.
• Maintenance and review.

48
Participants in Developing Expert Systems.

• The domain expert - the individual or group that
  has the expertise or knowledge one is trying to
  capture in the expert system.
• The knowledge engineer - an individual who has
  training and/or experience in the design,
  development, implementation, and maintenance of
  an expert system.

49
Participants in Developing Expert Systems.

• The knowledge user is the individual or group
  who uses and benefits from the expert system.
  Knowledge users do not need any previous training
  in computers or expert systems.

50
Difficulties of Knowledge Acquisition Process

• Transfer to a Machine, i.e., more detailed
• Number of participants, i.e., Expert, KE, system
  designer, user and the computer
• Knowledge expression difficulties
• Structuring the knowledge
• Not always cognitive in nature, feelings, memory
  sensations, etc.
• Lack of time from experts
• Complexity of testing and refining knowledge

51
Knowledge Elicitation Methods

• Interview Analysis
• Protocol Analysis
• Discussion of a Prototype
• Directed Interviews
• Informal Interviews
• Observations of Experts
• Questionnaires and Experts Reports
• Analysis of Documented Knowledge

52
Limitations of Questionnaires Expert Reports

• Require experts to act as KE
• Report bias Reflect how it should be done
  instead of how it is really done.
• Experts often include untested ideas
• Time consuming and experts lose interest
• Experts must be proficient in process documenting
  techniques such as flowcharting

53
Functional Applications of Expert Systems

• Accounting-related systems.
• Capital resource planning.
• Loan application analysis.
• Financial management.
• Manufacturing.
• Strategic marketing applications.

54
Examples of Expert Systems

• The Port of Singapore Authority Expert Systems
• planning and managing all operations of the port
• E.g., allocating berths to ships, planning the
  stowage of containers, the allocation of
  resources in general, and reading container
  numbers and operating trucking gates
• managing shipping traffic and the activities of
  the port
• E.g., assigning ships to anchorages, scheduling
  the movement of vessels through channels to
  terminals, deploying pilots to tugs and launches,
  routing launches, and deploying tugboats

55
Sample Expert Systems

• Whats wrong with your car? http//www.expertise
  2go.com/webesie/car/
• Buying the right PDA http//www.expertise2go.com/
  shop/pda.htm
• Choosing a Desktop PC http//www.expertise2go.com
  /shop/desktop.htm