decision support and business intelligence systems (8 th ed., prentice hall) chapter 4: modeling and...

Decision Support and Decision Support and Business Intelligence Business Intelligence

SystemsSystems(8(8thth Ed., Prentice Hall) Ed., Prentice Hall)

Chapter 4:Chapter 4:

Modeling and AnalysisModeling and Analysis

Copyright © 2011 Pearson Education, Inc. Publishing as Prentice Hall4-2

Major Modeling IssuesMajor Modeling Issues problem identification and environmental

analysis: scanning the environment to figure out what problems exist and can be solved via a model

variable identification: identifying the critical factors in a model and their relationships

ex: Influence diagram : Graphical representations of a model Rectangle = a decision variable Circle = uncontrollable or intermediate variable Oval = result (outcome) variable: intermediate or final

Variables are connected with arrows indicates the direction of influence (relationship)


Major Modeling IssuesMajor Modeling Issues forecasting: predicting the future

It is essential for construction models because when a decision implemented, the results occur in the future.

E-Commerce ( Information about purchases should be analyzed to predict demand)

5 Rights (How to get the right product(s) to the right customer at the right price at the right time in the right format

CRM and RMS rely heavily on forecasting techniques Predict the most profitable customers

use of multiple models: combining them to solve many parts of a complex problem

Each of which represents a different part of the decision – making problem

E.g., the Procter and Gamble supply chain DSS include: Location model to locate distribution centre , a product strategy

model, a demand- forecasting model, cost generation model ,….


Major Modeling IssuesMajor Modeling Issues use of multiple models

Types of models:

1. Standard : built in to DSS or freestanding soft ware that can interface with a DSS

2. Nonstandard : constructed from scratch. model categories: selecting the right type of model for

the problem or sub-problem (table 4.1)

model management: coordinating a firm’s models and their use

Models like data, must be managed to maintain their integrity and their applicability

Management is done by MBMS knowledge-based modeling: how to take advantage of

human knowledge in modeling DSS use mostly quantitive models, wheres Expert systems use

qualitiative


Categories of Models Categories of Models Table 4.1Table 4.1

Category Objective Techniques

Optimization of problems with few alternatives

Find the best solution from a small number of alternatives

Decision tables, decision trees

Optimization via algorithm

Find the best solution from a large number of alternatives using a step-by-step process

Linear and other mathematical programming models

Optimization via an analytic formula

Find the best solution in one step using a formula

Some inventory models

Simulation Find a good enough solution by experimenting with a dynamic model of the system

Several types of simulation

Heuristics Find a good enough solution using “common-sense” rules

Heuristic programming and expert systems

Predictive and other models

Predict future occurrences, what-if analysis, …

Forecasting, Markov chains, financial, …


Static and Dynamic ModelsStatic and Dynamic Models Static Analysis

Single snapshot of the situation, every thing occurs in a single interval

describes relationships among parts of a system at a point in time.

Ex: A decision about buy a product , Annual income statement.

Dynamic Analysis Evaluate scenarios that change over time

Time dependent Ex: In determining how many checkout points should

be open in a supermarket. A 5 year Profit and Loss projection in which input data

(costs, prices, and quantities ) change from year to year


MSS Modeling with SpreadsheetsMSS Modeling with Spreadsheets Spreadsheet: most popular end-user modeling

tool Flexible and easy to use Powerful functions

Add-in functions and solvers (small programs designed to extend the capabilities of a spreadsheet package)

Programmability (via macros) What-if analysis Goal seeking Simple database management Incorporates both static and dynamic models Examples: Microsoft Excel, Lotus 1-2-3


Types of Decision Making Types of Decision Making EnvironmentsEnvironments

Decision Making under Certainty Decision Making under Risk

(Decision making with probability) Decision Making Under Uncertainty

(Decision making without probability)


The Six Steps in Decision TheoryThe Six Steps in Decision Theory

1. Clearly define the problem at hand2. List all the possible alternatives (decisions to

be made)3. Identify the possible outcomes (state of

nature) of each alternative4. List the payoff or the profit of each

combination of alternatives and outcomes5. Select one of the mathematical decision

theory models (e.g. Decision Making under Risk)

6. Apply the model and make your decision


Certainty, Uncertainty and RiskCertainty, Uncertainty and Risk

The Zones of Decision Making


Decision Making:Treating CertaintyDecision Making:Treating Certainty Certainty Models

Assume complete knowledge All potential outcomes are known May yield optimal solution The decision maker knows exactly what the outcome of

each course of action will be. decision maker is to compute the optimal alternative

or outcome with some optimization criterion in mind. Ex: if the optimization criterion is least cost and you are

considering two different brands of a product, which appear to be equal in value to you, one costing 20% less than the other, then, all other things being equal, you will choose the less expensive brand.

decision making under certainty is rare because all other things are rarely equal.

Linear programming is one of the techniques for finding an optimal solution under certainty


Decision Making: Uncertainty and Decision Making: Uncertainty and RiskRisk Uncertainty

Several outcomes for each decision Probability of each outcome is unknown Knowledge would lead to less uncertainty Decision under uncertainty is very difficult Managers attempt to avoid uncertainty.

Instead they attempt to obtain more information so it can be treated under certainty Or

Some estimated probabilities are assigned to the outcomes and the decision making is done as if it is decision making under risk.


Decision Making Under Decision Making Under UncertaintyUncertainty Four Criteria MAXIMAX - find the alternative that maximizes the

maximum outcome for every alternative (Optimistic approach ) Ex: stocks

MAXIMIN - find the alternative that maximizes the minimum outcomes for every alternative (Pessimistic approach ) Ex : CDs

EQUALLY LIKELY- find the alternative with the highest average outcome

MINIMAX REGRET- minimizes the maximum regret (regret is the difference between the payoff from the best decision and all the other decision payoffs)


Decision Analysis: A Few Decision Analysis: A Few AlternativesAlternatives

Single Goal Situations 1. Decision tables :organize information and

knowledge in a systmatic ,tabular manner to prepare it for analysis

Multiple criteria decision analysis Features include :

Decision variables: describe alternatives course of variable),

Uncontrollable variables, Parameters : factors that effect the result variables nut not under control of decision maker

Result variables: reflect intermediate outcomes in mathematical models.


Decision Making: RiskDecision Making: Risk Risk analysis (probabilistic decision making)

Several outcomes for each decision Probability of each outcome is known Instead of optimizing the outcomes, the general rule

is to optimize the expected outcome. As an example: if you are faced with a choice

between two actions one offering a 1% probability of a gain of $10000 and the other a 50% probability of a gain of $400, you as a rational decision maker will choose the second alternative.


Investment Example Investment Example Decision Making Under RiskDecision Making Under Risk

Let us suppose that based on several economic forecasts, the investor is able to estimate

0.50% Solid Growth 0.30% Stagnation 0.20% Inflation

State of natureAlternative Solid Growth

. 50%Stagnation

.30%Inflation

.20%

Bonds 12 6 3

Stocks 15 3 -2

CDs 6.5 6.5 6.5



Risk analysis 1. Compute expected values or Expected payoff (EP) (outcome of first state of nature)*(its prob.) +

(outcome of second state of nature)*(its prob.)+…+ (outcome of last state of nature) * (its prob.) E.g. , In bonds yield = 12(.5)+6(.3)+3(.2) = 8.4 percent

The Best decision is the one with the greatest EP If the payoffs were in terms of costs, the best decision

would be the one with the lowest EP



2. Alternative approach in decision making under risk is to minimize expected opportunity loss (EOL).

Opportunity loss, also called regret EOL for an alternative is sum of all possible regrets of

alternative, each weighted by probability of state of nature for that regret occurring.

EOL (alternative i ) = (regret of first state of nature) x (probability of first state of nature) + (regret of second state of nature) x (probability of second state of nature) + . . . + (regret of last state of nature) x (probability of last state of nature)


Investment Example Investment Example Decision Making Under RiskDecision Making Under Risk EOL: Opportunity loss table (=regret table)


. 50%Stagnation

.30%Inflation

.20%EOL

$

Bonds 3 .5 3.5 2.35

Stocks 0 3.5 8.5 2.75

CDs 8.5 0 0 4.25

Min



3. The Maximum Likelihood Criterion Identify the state of nature with the largest Probability. 2. Choose the decisions alternative that has the

largest Payoff


. 50%Stagnation

.30%Inflation

.20%

Bonds 12 6 3

Stocks 15 3 -2

CDs 6.5 6.5 6.5



Expected Value of Perfect Information (EVPI) Is used to place an upper limit on what you should pay for

information that will aid in making a better decision. Is the increase in the EP that could be obtained if it were

possible to learn the true state of nature before making the decision

Is the difference between the expected value under certainty and the expected value under risk



Expected Value of Perfect Information (EVPI) EVPI = A – B A = expected value with perfect information B = expected value without perfect information For A: The optimal values for each value are:

Max Value (A)= 15*.5 +6.5*.3 +6.5*.2 =10.75


. 50%Stagnation

.30%Inflation

.20%

Bonds 12 6 3

Stocks 15 3 -2

CDs 6.5 6.5 6.5



Expected Value of Perfect Information (EVPI) B = expected value without perfect information For B: we compute the expected values for each

column first, and then select the max as below:

EVPI = 10.75-8.4 = 2.55 $


Decision Analysis: A Few Decision Analysis: A Few AlternativesAlternatives

Single Goal Situations Decision trees

Graphical representation of relationships Multiple criteria approach Demonstrates complex relationships Cumbersome, if many alternatives exists

How can a decision tree be used in decision making?By showing the decision maker the possible outcomes that could result from a given choice, the tree gives the decision maker information by which to compare choices


Decision treesDecision trees The Five Steps

1. Define the problem2. Structure or draw the decision tree3. Assign probabilities to the states of nature4. Estimate the payoffs for each possible combination

of alternative and state of nature Solve the problem by computing expected payoff (EP) for each state of nature node

5. Make your decision


Decision Tree Example (Self Decision Tree Example (Self Study)Study) This is just a beginning of ADM2302 course and Andrew does not know

if he should attend all classes. He consulted some other students and came to the following conclusions:• chances of passing a course while attending all classes are 80%• chances of passing a course while attending randomly are 50%.It is well known that professor who is teaching that course is giving

second chance to the students who failed. They have to solve a pretty nasty case study.

Again, Andrew estimates that chances of solving this case if he would go to all the classes are 60%, while they drop to just 10% if he would attend classes randomly.

Andrew would be very happy if he passes the course (5 on a happiness scale of 0 - 5). Clearly, he would be very disappointed if he fails (0 on a happiness scale).

Going to a classroom requires an effort and diminished happiness associated with passing the course.

It goes down by 3 points (happiness scale) for attending all classes and 1 point for 39 random attendance.


Optimization Optimization via Mathematical Programmingvia Mathematical Programming Mathematical Programming

A family of tools designed to help solve managerial problems in which the decision maker must allocate scarce resources among competing activities to optimize a measurable goal

Optimal solution: The best possible solution to a modeled problem Linear programming (LP): A mathematical model

for the optimal solution of resource allocation problems. All the relationships are linear Limited quantity of economic resources Allocation is usually restricted by constraints


LineLine

Linear Programming StepsLinear Programming Steps 1. Identify the …

Decision variables Objective function Objective function coefficients Constraints

Capacities / Demands

2. Represent the model LINDO: Write mathematical formulation EXCEL: Input data into specific cells in Excel

3. Run the model and observe the results


Sensitivity, What-if, and Sensitivity, What-if, and Goal Seeking AnalysisGoal Seeking Analysis Sensitivity

Assesses impact of change in inputs on outputs Eliminates or reduces variables Can be automatic or trial and error

1. Automatic Sensitivity analysis is performed in standard quantitative model implementation such as LP

2. Trial and Error Change in any variable or in several Two approaches: What-if and Goal Seeking


Sensitivity, What-if, and Sensitivity, What-if, and Goal Seeking AnalysisGoal Seeking Analysis

What-if Assesses solutions based on changes in variables

or assumptions (scenario analysis) Ex: What will happen to the total inventory cost if

the cost of carrying inventories increases by 10 percent?


Sensitivity, What-if, and Sensitivity, What-if, and Goal Seeking AnalysisGoal Seeking Analysis

Goal seeking Backwards approach, starts with goal Determines values of inputs needed to achieve

goal Ex: what annual R&D budget is needed for an annual

growth rate of 15 percent by 2014?


Sensitivity, What-if, and Sensitivity, What-if, and Goal Seeking AnalysisGoal Seeking Analysis Computing a Break-Even Point Using Goal

Seeking Values that generate zero profit Break –Even= Fixed cost / (selling cost – variable

cost) Where : fixed cost =cost that not change such as tax,

insurance ,.. Selling price: the price that a unit sold for Variable cost : related to production unit.


Problem –Solving Search Problem –Solving Search MethodsMethods

Search methods used in the choice phase of problem solving includes:

Analytical techniques , algorithms , blind searching and heuristic searching

For normative models (Comparing all the outcomes of alternative) :

analytical approach is used For descriptive models(a comparison of a limited number

of alternatives is used) : blindly or heuristic s are used.



Analytical Techniques Use mathematical formulas to derive optimal solution Solving structured problems (tactical or operational) Ex: inventory management, resource allocation. Analytical Techniques may use Algorithms

Algorithms Step by step search process Obtaining an optimal solution

Web search engines use algorithms To speed searches and produces accurate results



Blind Searching Problem solving is done by searching through the possible

solutions The first search methods of problem solving Arbitrary search approaches that are not guided Two types:

A complete enumeration : all alternatives are considered to find an optimal solution.

Incomplete (Partial) : continues until a good –enough solution is found

Heuristic Searching Informal judgmental knowledge of an application area that

constitute the rules of the good judgment in the field.


SimulationSimulation

Simulation is a process of designing a model of real system a model of real system

purpose of understanding the behavior for the operation of the behavior for the operation of the system.

Frequently used in DSS tools


SimulationSimulation System:

Collection of entities, ex: people machines that act and interact towards the accomplishment.

State: Collection of variables necessary to describe a system at a

particular time relative to the objective of study Bank model: Could include number of busy tellers, time of arrival

of each customer, etc System can be 1. Discrete

State variables change instantaneously at separated points in time

Bank model: State changes occur only when a customer arrives or departs


2. Continuous State variables change that continuously tracks system

response over time Airplane flight: State variables like position, velocity

change continuously


Imitates reality and capture its richness Technique for conducting experiments Descriptive, not normative tool Often to “solve” very complex problems

Simulation is normally used only when a problem is too complex to be treated using numerical optimization techniques

Major Characteristics of Major Characteristics of SimulationSimulation

!!


Advantages of SimulationAdvantages of Simulation The theory is fairly straightforward Great deal of time compression Experiment with different alternatives The model reflects manager’s perspective Can handle wide variety of problem types Can include the real complexities of

problems Produces important performance measures Often it is the only DSS modeling tool for

non-structured problems


Limitations of SimulationLimitations of Simulation

Cannot guarantee an optimal solution Slow and costly construction process Cannot transfer solutions and inferences

to solve other problems (problem specific)

Software may require special skills


Simulation MethodologySimulation Methodology Model real system and conduct repetitive experiments. Steps:

1. Define problem 5. Conduct experiments2. Construct simulation model 6. Evaluate results3. Test and validate model 7. Implement solution4. Design experiments


Visual interactive modeling (VIM)Also called Visual interactive problem solving Visual interactive modeling Visual interactive simulation

Uses computer graphics to present the impact of different management decisions

Often integrated with GIS Users perform sensitivity analysis Static or a dynamic (animation) systems

Visual Interactive Modeling (VIM) Visual Interactive Modeling (VIM) / Visual Interactive Simulation / Visual Interactive Simulation (VIS)(VIS)

decision support and business intelligence systems (8 th ed., prentice hall) chapter 4: modeling and...

Documents