Chapter 5: Modeling and Analysis

Some successful models and
methodologies
–
–
–
–
–
decision analysis
decision trees
optimization
heuristic programming
simulation
Opening Vignette: Siemens Solar
Industries

Problems in photocell fabrication
–

Clean room contamination-control
technology
–
–


improve quality, fewer defects, reduced cycletimes?
No experience
Use simulation: a virtual laboratory
Major benefit:
–
–

poor material flow, unbalanced resource use,
throughput bottlenecks, schedule delays
knowledge and insight on interactions in systems
evaluate alternative scheduling policies, delivery
rules, with respect to queue-levels, throughput,
machine utilization, WIP levels, etc
Improved the manufacturing process
Modeling for MSS



Key element in most DSS
A necessity in a model-based DSS
Use of Multiple models
(Frazee Paint Company Example -- Appendix A)
Three model types
1. Statistical model (regression analysis)
2. Financial model (IFPS)
3. Optimization model (LP)

Collective use of standard and custommade models
Major Modeling Issues








Problem identification
Environmental analysis
Variable identification
Forecasting
Multiple model use
Model categories (or selection)
Model management
Knowledge-based modeling
T A B L E 5 .1 C a teg o ries o f M o d els.
C ateg o ry
Pro cess and O bjectiv e
R epresentativ e T echniques
O ptim izatio n o f pro blem s
w ith few alternativ es (S ectio n
5 .7 )
Find the best so lutio n fro m a
relativ ely sm all num ber o f
alternativ es
D ecisio n tables, decisio n trees
O ptim izatio n v ia alg o rithm
(S ectio n 5 .8 )
Find the best so lutio n fro m a
larg e o r an infinite num ber o f
alternativ es using a step-by step im pro v em ent pro cess
L inear and o ther
m athem atical pro g ram m ing
m o dels, netw o rk m o dels
O ptim izatio n v ia analy tical
fo rm ula (S ectio ns 5 .8 , 5 .1 2 )
Find the best so lutio n, in o ne
step, using a fo rm ula
S o m e inv ento ry m o dels
S im ulatio n (S ectio n 5 .1 0 ,
5 .1 5 )
Finding " g o o d eno ug h"
so lutio n, o r the best am o ng
tho se alternativ es checked,
using experim entatio n
S ev eral ty pes o f sim ulatio n
H euristics (S ectio n 5 .9 )
Find " g o o d eno ug h" so lutio n
using rules
H euristic pro g ram m ing ,
expert sy stem s
O ther m o dels
Finding " w hat-if" using a
fo rm ula
Financial m o deling , w aiting
lines
Predictiv e m o dels (W eb
Pag e)
Predict future fo r a g iv en
scenario
Fo recasting m o dels, M arko v
analy sis
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Static and Dynamic Models

Static Analysis
–

Single snapshot
Dynamic Analysis
–
–
–
–
–
Dynamic models
Evaluate scenarios that change over time
Are time dependent
Show trends and patterns over time
Extended static models
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Treating Certainty, Uncertainty,
and Risk



Certainty Models
Uncertainty
Risk
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Influence Diagrams



Graphical representations of a model to assist
in model design, development and
understanding
Provide visual communication to the model
builder or development team
Serve as a framework for expressing the MSS
model relationships
= a decision variable
= uncontrollable or intermediate variable
= result (outcome) variable: intermediate or final
Variables connected with arrows
U n it P r ic e
~
A m o u n t u s e d in
a d v e r tis e m e n t
In c o m e
U n its S o ld
P r o f it
E xp ense
U n it C o s t
F ix e d
C o st
P r o f it = I n c o m e - E x p e n s e
I n c o m e = U n its S o ld x U n it P r ic e
U n its S o ld = 0 . 5 x A m o u n t u s e d in A d v e r tis e m e n t
E x p e n s e s = U n it C o s t x U n its s o ld + F ix e d c o s t
F I G U R E 5 . 1 A n I n f lu e n c e D ia g r a m f o r t h e P r o f it M o d e l.
MSS Modeling in Spreadsheets







(Electronic) spreadsheet: most popular enduser modeling tool
Powerful financial, statistical, mathematical,
logical, date/time, string functions
Multidimensional analysis
External add-in functions and solvers
Programmability (macros)
Seamless integration with other tools
What-if analysis, Goal seeking, etc.
Decision Analysis of Few Alternatives
(Decision Tables and Trees)

Single Goal Situations
–

Decision tables, Decision trees
Investment Example
One goal: Maximize the yield after one year
Yield depends on the status of the economy (states of
nature)
•
Solid growth, Stagnation, Inflation
1. If there is solid growth in the economy, bonds will yield 12
percent; stocks, 15 percent; and time deposits, 6.5 percent
2. If stagnation prevails, bonds will yield 6 percent; stocks, 3
percent;
and time deposits, 6.5 percent
3. If inflation prevails, bonds will yield 3 percent; stocks will
bring a loss
of 2 percent; and time deposits will yield
6.5 percent
View problem as a two-person
game

Payoff Table
–
–
–
Decision variables (the alternatives)
Uncontrollable variables (the states of the
economy)
Result variables (the projected yield)
In v e s tm e n t P r o b le m D e c is io n T a b le M o d e l.
S ta te s o f N a tu r e (U n c o n tr o lla b le V a r ia b le s )
A lte r n a tiv e
S o lid G r o w th
S ta g n a tio n
Bonds
1 2 .0 %
6 .0 %
3 .0 %
S to c k s
1 5 .0 %
3 .0 %
- 2 .0 %
6 .5 %
6 .5 %
6 .5 %
CDs
In fla tio n
Uncertainty and Risk

Treating Uncertainty
–

Optimistic approach, Pessimistic
approach
Treating Risk
–
–
–
Use known probabilities
Risk analysis: Compute expected values
can be dangerous
D ecision U nder R isk and Its S olution.
S olid G row th
S tagnation
Inflation
E xpected
0.50
0.30
0.20
V alue
B onds
12.0%
6.0%
3.0%
8.4% (M ax)
S tocks
15.0%
3.0%
- 2.0%
8.0%
6.5%
6.5%
6.5%
6.5%
Alternative
CDs


Decision Trees
Other Methods of Treating Risk
–
–
–
Simulation
Certainty factors
Fuzzy logic.
Multiple Goals

Yield, safety, and liquidity
M u ltip le G o a ls .

A lte rn a tiv e s
Y ie ld
S a fe ty
L iq u id ity
Bonds
8 .4 %
H ig h
H ig h
S to c k s
8 .0 %
Low
H ig h
CDs
6 .5 %
V e ry H ig h
H ig h
Analytic Hierarchy Process
Optimization via Mathematical
Programming


Linear programming (LP) used
extensively in DSS
Mathematical Programming
Family of tools to solve managerial
problems in allocating scarce resources
among various activities to optimize a
measurable goal
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Heuristic Programming





Reduces search using heuristics
Gets satisfactory solutions more quickly
and less expensively
Finds rules to solve complex problems
Heuristic programming finds feasible and
"good enough" solutions to some
complex problems
Heuristics can be
–
–
Quantitative
Qualitative (in ES)
When to Use Heuristics
1. Inexact or limited input data
2. Complex reality
3. Reliable, exact algorithm not available
4. Simulation computation time too
excessive
5. To improve the efficiency of optimization
6. To solve complex problems
7. For symbolic processing
8. For solving when quick decisions are to
be made
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Advantages of Heuristics
1. Simple to understand: easier to implement and
explain
2. Help train people to be creative
3. Save computer running time (speed)
4. Frequently produce multiple acceptable
solutions
5. Usually possible to develop a measure of
solution quality
6. Can incorporate intelligent search
7. Can solve very complex models
Limitations of Heuristics
1. Cannot guarantee an optimal solution
2. There may be too many exceptions
3. Sequential decision choices can fail to
anticipate future consequences of each
choice
4. Interdependencies of subsystems can
influence the whole system

Heuristics successfully applied to vehicle
routing
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Simulation



A technique for conducting experiments
with a computer on a model of a
management system
Frequently used DSS tool
Major Characteristics of Simulation
–
–
–
–
Simulation imitates reality and capture its
richness
Simulation is a technique for conducting
experiments
Simulation is a descriptive not normative tool
Simulation is often used to solve very complex,
risky problems
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Advantages of Simulation
1. Theory is straightforward
2. Time compression
3. Descriptive, not normative
4. Intimate knowledge of the problem required,
forces the MSS builder to interface with the
manager
5. The model is built from the manager's
perspective
6. Simulation model built for specific problem;
no generalized understanding is required of
the manager. Each model component
represents a real problem component
7. Can handle a wide variety of problem
types
8. Can experiment with different variables
9. Allows for real-life problem complexities
10. Easy to obtain many performance
measures directly
11. Frequently the only DSS modeling tool
for handling nonstructured problems
Limitations of Simulation
1. Cannot guarantee an optimal solution
2. Slow and costly construction process
3. Cannot transfer solutions and inferences
to solve other problems
4. So easy to sell to managers, may miss
analytical solutions
5. Software is not so user friendly
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Simulation Methodology

Set up a model of a real system and
conduct repetitive experiments
1. Problem Definition
2. Construction of the Simulation Model
3. Testing and Validating the Model
4. Design of the Experiments
5. Conducting the Experiments
6. Evaluating the Results
7. Implementation
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Simulation: Issues

Probabilistic Simulation
–
–

Use of random numbers
–


Discrete distributions
Continuous distributions
Replications with different random number
streams
Simulation Software
Visual Simulation
D is c re te ve rs u s C o n tin u o u s
D is c re te
C o n tin u o u s
D a ily D e m a n d
P ro b a b ility
5
0 .1 0
N o rm a lly
6
0 .1 5
d is trib u te d w ith
7
0 .3 0
a m ean of
8
0 .2 5
7 a n d a s ta n d a rd
9
0 .2 0
d e via tio n o f 1 .2
Multidimensional Modeling





From a spreadsheet and analysis
perspective
2-D to 3-D to multiple-D
Multidimensional modeling tools: 16-D +
Multidimensional modeling: four views of the
same data
Tool can compare, rotate, and "slice and
dice" corporate data across different
management viewpoints
Visual Spreadsheets



User can visualize the models and
formulas using influence diagrams
Not cells, but symbolic elements
English-like modeling
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Financial and Planning Modeling

Special tools to build usable DSS
rapidly, effectively, and efficiently

The models are algebraically oriented
Fourth generation programming languages
Models written in an English-like syntax
Models are self-documenting
Model steps are nonprocedural




D S S In F o cu s 5 .6 : T y p ica l A p p lica tio n s o f P la n n in g M o d els
F in a n cia l fo reca stin g
M a n p o w er p la n n in g
P ro fo rm a fin a n cia l sta tem en ts
P ro fit p la n n in g
C a p ita l b u d g etin g
S a les fo reca stin g
M a rk et d ecisio n m a k in g
In v estm en t a n a ly sis
M erg ers a n d a cq u isitio n s a n a ly sis
C o n stru ctio n S ch ed u lin g
L ea se v ersu s p u rch a se d ecisio n s
T a x P la n n in g
P ro d u ctio n sch ed u lin g
E n erg y req u irem en ts
N ew v en tu re ev a lu a tio n
L a b o r co n tra ct n eg o tia tio n fees
F o reig n cu rren cy a n a ly sis
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Visual Modeling and Simulation

Visual interactive modeling (VIM). Also
called:
–
–
–




Visual interactive problem solving
Visual interactive modeling
Visual interactive simulation
Use computer graphics to present the
impact of different management decisions.
Users perform sensitivity analysis
Static or a dynamic (animation) systems
Visual Interactive Simulation
–
Decision makers interact with the simulated
model and watch the results over time
Ready-made Quantitative
Software Packages


Preprogrammed models can expedite the
programming time of the DSS builder
Some models are building blocks of other
quantitative models
–
–
–
–
–
Statistical Packages
Management Science Packages
Financial Modeling
Other Ready-Made Specific DSS (Applications)
including spreadsheet add-ins
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
T A B L E 5 .7 R ep resen tative R ead y -m ad e S p ecific D S S
N am e of
P ack age
A u toM od ,
A u toS ch ed
V en d or
D escrip tion
A u toS im u lation s
B ou n tifu l, U T
h ttp ://w w w .au tosim .com
3 D w alk -th rou gh an im ation s for m an u factu rin g
an d m aterial h an d lin g;
M an u factu rin g sch ed u lin g
B u d getin g &
R ep ortin g
H elm sm an G rou p , In c.
P lain sb oro, N J
http://w w w .helm sm angroup.com
F in an cial d ata w areh ou sin g
F A C T O R /A IM
P A C K A G IN G
P ritsk er C orp .
In d ian ap olis, IN
h ttp ://w w w .p ritsk er.com
M an u factu rin g sim u lator w ith costin g cap ab ilities,
H igh sp eed /h igh volu m e food an d b everage
in d u stry sim u lator
M ed M od el,
S erviceM od el
P roM od el C orp .
O rem , U T
h ttp ://w w w .p rom od el.com
H ealth care sim u lation ,
S ervice in d u stry sim u lation
O IS
O lsen & A ssociates L td .
Z ü rich , S w itzerlan d
h ttp ://w w w .olsen .ch
D irection al forecasts,
trad in g m od els,
risk m an agem en t
O p tiP lan
P rofession al,
O p tiC ap s,
O p tiC alc
A d van ced P lan n in g S y stem s, In c.
A lp h aretta, G A
S u p p ly ch ain p lan n in g
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Model Base Management





MBMS: capabilities similar to that of
DBMS
But, there are no comprehensive model
base management packages
Each organization uses models
somewhat differently
There are many model classes
Some MBMS capabilities require
expertise and reasoning
Desirable Capabilities of
MBMS





Control, Flexibility
Feedback
Interface
Redundancy Reduction, Increased
Consistency
MBMS Design Must Allow the DSS User to
1. Access and retrieve existing models.
2. Exercise and manipulate existing models
3. Store existing models
4. Maintain existing models
5. Construct new models with reasonable effort
SUMMARY



Models play a major role in DSS
Models can be static or dynamic.
Analysis is under assumed certainty, risk,
or uncertainty
–
–
–

Influence diagrams
Electronic spreadsheets
Decision tables and decision trees
Optimization tool: mathematical
programming
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
SUMMARY (cont’d.)







Linear programming: economic-base
Heuristic programming
Simulation
Simulation can deal with more complex
situations
Expert Choice
Forecasting methods
Multidimensional modeling
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
SUMMARY (cont’d.)







Built-in quantitative models (financial,
statistical)
Special financial modeling languages
Visual interactive modeling
Visual interactive simulation (VIS)
Spreadsheet modeling and results in
influence diagrams
MBMS are like DBMS
AI techniques in MBMS
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Debate

Some people believe that managers
do not need to know the internal
structure of the model and the
technical aspects of modeling. “It is
like the telephone or the elevator, you
just use it.” Others claim that this is
not the case and the opposite is true.
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson
Copyright 1998, Prentice Hall, Upper Saddle River, NJ
Descargar

Chapter 5 Modeling and Analysis