Short Ch05

Embed Size (px)

Citation preview

  • 8/6/2019 Short Ch05

    1/35

    1

    CHAPTER 5

    Modeling and Analysis

  • 8/6/2019 Short Ch05

    2/35

    2

    Modeling and Analysis

    s Major DSS component

    s Model base and model management

    s CAUTION - Difficult Topic Ahead

    Familiarity with major ideas

    Basic concepts and definitions

    Tool--influence diagram

    Model directly in spreadsheets

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    3/35

    3

    s Structure of some successful models and

    methodologies Decision analysis

    Decision trees

    Optimization

    Heuristic programming Simulation

    s New developments in modeling tools / techniques

    s Important issues in model base management

    Modeling and Analysis

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    4/35

    4

    Major Modeling Issues

    s Problem identification

    s Environmental analysis

    s Variable identification

    s Forecastings Multiple model use

    s Model categories or selection (Table 5.1)

    s

    Model managements Knowledge-based modeling

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    5/35

    5

    Static and Dynamic Models

    s Static Analysis

    Single snapshot

    s Dynamic Analysis

    Dynamic models

    Evaluate scenarios that change overtime

    Time dependent

    Trends and patterns over timeExtend static models

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    6/35

    6

    Treating Certainty,

    Uncertainty, and Risk

    s Certainty Models

    s

    s Uncertainty

    s

    s Risk

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    7/35

    7

    Influence Diagrams

    s

    Graphical representations of a models Model of a model

    s Visual communication

    s Some packages create and solve the mathematical model

    s Framework for expressing MSS model relationships Rectangle = a decision variable

    Circle = uncontrollable or intermediate variable

    Oval = result (outcome) variable: intermediate or final

    Variables connected with arrows

    Example (Figure 5.1)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    8/35

    8Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    9/35

    9

    Analytica Influence Diagram of a MarketingProblem: The Marketing Model (Figure 5.2a)

    (Courtesy of Lumina Decision Systems, Los Altos, CA)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    10/35

    10

    MSS Modeling in Spreadsheets

    s Spreadsheet: most popular end-user modeling tools Powerful functions

    s Add-in functions and solvers

    s Important for analysis, planning, modeling

    s Programmability (macros) (More)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    11/35

    11

    s What-if analysis

    s Goal seeking

    s Simple database management

    s Seamless integration

    s Microsoft Excel

    s Lotus 1-2-3

    s

    s Excel spreadsheet static model example of a simpleloan calculation of monthly payments (Figure5.3)

    s

    s Excel spreadsheet dynamic model example of asimple loan calculation of monthly payments andeffects of prepayment (Figure 5.4)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    12/35

    12

    Decision Analysisof Few Alternatives

    (Decision Tables and Trees)

    Single Goal Situations

    s

    s Decision tables

    s

    s Decision trees

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    13/35

    13

    Decision Tables

    s Investment example

    s One goal: maximize the yield after one year

    s Yield depends on the status of the economy

    (thestate of nature)

    Solid growth

    Stagnation

    Inflation

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    14/35

    14

    1. If solid growth in the economy, bonds yield12%; stocks 15%; time deposits 6.5%

    2. If stagnation, bonds yield 6%; stocks 3%;

    time deposits 6.5%

    3. If inflation, bonds yield 3%; stocks lose 2%;time deposits yield 6.5%

    Possible Situations

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    15/35

    15

    View Problem as a Two-Person Game

    Payoff Table 5.2s

    s Decision variables (alternatives)

    s

    s Uncontrollable variables (states of economy)

    s

    s Result variables (projected yield)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    16/35

    16

    Table 5.2: Investment ProblemDecision Table Model

    States of Nature

    Solid Stagnation Inflation

    Alternatives Growth

    Bonds 12% 6% 3%

    Stocks 15% 3% -2%

    CDs 6.5% 6.5% 6.5%

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    17/35

    17

    Treating Uncertainty

    s Optimistic approach

    s

    s Pessimistic approach

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    18/35

    18

    Treating Risk

    s Use known probabilities (Table 5.3)

    s

    s

    Risk analysis: compute expected valuess

    s Can be dangerous

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    19/35

    19

    Table 5.3: Decision Under Risk and ItsSolution

    Solid Stagnation Inflation Expected

    Growth Value

    Alternatives .5 .3 .2

    Bonds 12% 6% 3% 8.4% *

    Stocks 15% 3% -2% 8.0%

    CDs 6.5% 6.5% 6.5% 6.5%

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    20/35

    20

    s Decision Trees

    s Other methods of treating risk Simulation

    Certainty factors

    Fuzzy logic

    s Multiple goals

    s Yield, safety, and liquidity (Table 5.4)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    21/35

    21

    Table 5.4: Multiple Goals

    Alternatives Yield Safety Liquidity

    Bonds 8.4% High High

    Stocks 8.0% Low High

    CDs 6.5% Very High High

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    22/35

    22

    Optimization via MathematicalProgramming

    s Linear programming (LP)

    Used extensively in DSS

    s Mathematical Programming Family of tools to solve managerial problems

    in allocating scarce resources among

    various activities to optimize a measurablegoal

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    23/35

    23

    LP AllocationProblem Characteristics

    1. Limited quantity of economic resources

    2. Resources are used in the production ofproducts or services

    3. Two or more ways (solutions, programs)to use the resources

    4. Each activity (product or service) yieldsa return in terms of the goal

    5. Allocation is usually restricted byconstraints

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th editionCopyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    24/35

    24

    LP Allocation Model

    s Rational economic assumptions 1. Returns from allocations can be compared in a common

    unit

    2. Independent returns

    3. Total return is the sum of different activities returns

    4. All data are known with certainty

    5. The resources are to be used in the most economicalmanner

    s Optimal solution: the best, found algorithmically

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    25/35

    25

    Linear Programming

    s Decision variables

    s Objective function

    s

    Objective function coefficientss Constraints

    s Capacities

    s Input-output (technology) coefficients

    Line

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    26/35

    26

    Heuristic Programming

    s Cuts the search

    s Getssatisfactory solutions more quickly and lessexpensively

    s Finds rules to solve complex problems

    s Finds good enough feasible solutions to complex problems

    s Heuristics can be

    Quantitative

    Qualitative (in ES)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    27/35

    27

    When to Use Heuristics

    1. Inexact or limited input data

    2. Complex reality

    3. Reliable, exact algorithm not available

    4. Computation time excessive5. To improve the efficiency of optimization

    6. To solve complex problems

    7. For symbolic processing

    8. For making quick decisions

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    28/35

    28

    Simulation

    s Technique for conducting experiments with acomputer on a model of a management system

    s

    s Frequently used DSS tool

    s

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    29/35

    29

    Major Characteristics of Simulation

    s Imitates reality and capture its richness

    s

    s Technique for conducting experiments

    s

    s Descriptive, not normative tool

    s

    s Often to solve very complex, risky problems

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    30/35

    30

    Simulation Methodology

    Model real system and conduct repetitiveexperiments

    1. Define problem

    2. Construct simulation model 3. Test and validate model

    4. Design experiments

    5. Conduct experiments

    6. Evaluate results 7. Implement solution

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    31/35

    31

    Multidimensional Modeling

    s Performed in online analytical processing (OLAP)

    s From a spreadsheet and analysis perspective

    s 2-D to 3-D to multiple-D

    s Multidimensional modeling tools: 16-D +s Multidimensional modeling - OLAP (Figure 5.6)

    s Tool can compare, rotate, and slice and dicecorporate data across different management

    viewpoints

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

    Vi l I t ti M d li (VIS) d

  • 8/6/2019 Short Ch05

    32/35

    32

    Visual Interactive Modeling (VIS) andVisual Interactive Simulation (VIS)

    s Visual interactive modeling (VIM) (DSS In Action 5.8)Also called

    Visual interactive problem solving

    Visual interactive modeling

    Visual interactive simulation

    s Use computer graphics to present the impact of differentmanagement decisions.

    s Can integrate with GIS

    s Users perform sensitivity analysis

    s Static or a dynamic (animation) systems (Figure 5.7)

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    33/35

    33

    Visual Interactive Simulation (VIS)

    s Decision makers interact with the simulatedmodel and watch the results over time

    s Visual interactive models and DSS

    VIM (Case Application W5.1 on books Website)

    Queueing

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    34/35

    34

    Quantitative Software Packages-OLAP

    s Preprogrammed models can expedite DSSprogramming time

    s Some models are building blocks of other models

    Statistical packages

    Management science packages

    Revenue (yield) management

    Other specific DSS applications including spreadsheet add-ins

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ

  • 8/6/2019 Short Ch05

    35/35

    35

    Model Base Management

    s MBMS: capabilities similar to that of DBMS

    s But, there are no comprehensive model base managementpackages

    s Each organization uses models somewhat differently

    s There are many model classess Within each class there are different solution approaches

    s Some MBMS capabilities require expertise and reasoning

    Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition

    Copyright 2001, Prentice Hall, Upper Saddle River, NJ