Multiple Attribute Niken Iwani Surya

Putri

Decision Making MDM after mid

2020
Decision Making Process
2
MCDM Definition
Multiple criteria decision making (MCDM) refers to making decisions in the
presence of multiple, usually conflicting, criteria.

Terms for MCDM environment:

• 1. Criteria: A criterion is a measure of effectiveness. It is the basis
for evaluation. Criteria are emerging as a form of attributes or
objectives in the actual problem setting.
• 2. Goals: Goals (synonymous with targets) are a priori values or
levels of aspiration.
• These are to be either achieved or surpassed or not exceeded.
• Often we refer to them as constraints because they are
designed to limit and restrict the alternative set. For example,
the standard gas mileage, say 20 miles/gallon, set up by the
federal government for 1980 models, is a constraint, whereas
30 miles/gallon may serve as a goal for the car manufacturer.
 Terms for MCDM environment:

3. Attributes: Performance parameters,

components, factors, characteristics, and properties
are synonyms for attributes. An attribute should
provide a means of evaluating the levels of an
objective. Each alternative can be characterized by a
number of attributes (chosen by DM's conception
of criteria), i.e., gas mileage, purchasing cost,
MCDM horsepower, etc. of a car.

Definition 4. Objectives: An objective is something to be

pursued to its fullest. For example, a car
manufacturer may want to maximize gas mileage or
minimize production cost or minimize its level of air
pollution. An objective generally indicates the
direction of change desired.
 Example of MCDM problems are:
1. In a personal context, one buys car may be
MCDM based on criteria such as price, gas mileage,
style, safety, comfort, etc. A young
Definition man/woman may choose a wife/husband
based on her/his intelligence, looks,
character, wealth.
 Example of MCDM problems are:
1. In the business context, a business
executive's choice of corporate
strategy may depend on the
company's earnings over a period
of time, its stock price, share of
market, goodwill, labor relations,
MCDM corporate image, obligation to
society, and so forth. Another case
Definition is when automobile
manufacturers in Pulogadung
want to design a model which
maximizes fuel efficiency,
maximizes riding comfort,
minimizes production cost, etc.
 Example of MCDM problems are:
1. In the public context, the water
resources development plan for a
community should be evaluated in
MCDM terms of cost, probability of water
shortage, energy (reuse factor),
Definition recreation, flood protection, land and
forest use, water quality.
 1. Multiple objectives/attributes. Each problem
has multiple objectives/ attributes. A decision
maker must generate relevant
objectives/attributes for each problem setting.
2. Conflict among criteria. Multiple criteria
usually conflict with each other. For example,
in designing a car, the objective of higher gas
Characteristics mileage might reduce the comfort rating due
of Problems in to the smaller passenger space.
MCDM 3. Incommensurable units. Each
objective/attribute has a different unit of
measurement. In the car selection case, gas
mileage is expressed by miles per gallon
(MPG), comfort is by cu ft if it is measured by
passenger space, safety may be indicated in a
non numerical way, cost is indicated by
dollars.
Goal for To design or to choose or to create an
alternative that is the most attractive
MCDM over all criteria (dimensions).
 1. Non dominated solutions: This
solution is named differently by
different disciplines: non
Solutions in dominated solution, non inferior
solution, and efficient solution in
MADM MCDM, a set of admissible
alternatives in statistical decision
theory, and Pareto-optimal
solution in economics.
 2. Satisfying solutions: A satisfying solution
of Simon [373] is a reduced subset of
the feasible set which exceeds all of
the aspiration levels of each attribute.
A set of satisfying solutions is
Solutions in composed of acceptable alternatives.
MADM Satisfying solutions need not be non
dominated. This solution is credited for
its simplicity which matches the
behavior process of the DM whose
knowledge and ability are limited-
bounded rationality.
 3. Preferred solution: A preferred
solution: A preferred solution is a
non dominated solution elected
Solutions in as the final choice through the
DM's involvement in the
MADM information processing. In this
respect the MCDM can be
referred to as the decision aids
reach the preferred solution
through utilizing the DM's
preference information.
Sistem Hirarki MCDM
Decomposing Problem
 • 1. AHP
Methods in • 2. Scoring Model
MCDM • 3. Rating
• 4. Simple Sequel Elimination
 Problem solving steps:

Establish Identify Identify

Establish the Identify the Identify the criteria
decision context, alternatives. (attributes) that
the decision are relevant to the
objectives (goals), decision problem.
and identify the
decision maker(s).

16
Problem solving
steps:
• 4) For each of the criteria,
assign scores to measure
the performance of the
alternatives against each of
these and construct an
evaluation matrix (often
called an options matrix or
a decision table).

17
Problem Standardize
solving
steps: • Standardize the raw scores
to generate a priority
scores matrix or decision
table.

Determine

• Determine a weight for

each criterion to reflect
how important it is to the
overall decision.
 19

Problem solving steps:

7) Use aggregation functions

8) Perform a sensitivity analysis
(also called decision rules) to
to assess the robustness of the
compute an overall assessment
preference ranking to changes
measure for each decision
in the criteria scores and/or the
alternative by combining the
assigned weights.
weights and priority scores.
Analytical Hierarchy Process (AHP)

■ Method for ranking several decision alternatives and selecting

the best one when the decision maker has multiple objectives,
or criteria, on which to base the decision.
■ The decision maker makes a decision based on how the
alternatives compare according to several criteria.
■ The decision maker will select the alternative that best meets the
decision criteria.
■ A process for developing a numerical score to rank each decision
alternative based on how well the alternative meets the decision
maker’s criteria.
Analytical Hierarchy Process
Example Problem Statement

Southcorp Development Company shopping mall site selection.

■ Three potential sites:
§ Atlanta
§ Birmingham
§ Charlotte.
■ Criteria for site comparisons:
§ Customer market base.
§ Income level
§ Infrastructure
§ Transportation
Analytical Hierarchy Process
Hierarchy Structure
■ Top of the hierarchy: the objective (select the best site).

■ Second level: how the four criteria contribute to the objective.

■ Third level: how each of the three alternatives contributes to

each of the four criteria.
Analytical Hierarchy Process
Pairwise Comparisons (1 of 2)

■ In a pairwise comparison, two alternatives are compared

according to a criterion and one is preferred.

■ A preference scale assigns numerical values to different levels of

performance.
Analytical Hierarchy Process
Pairwise Comparisons (2 of 2)

Table 9.1 Preference scale for pairwise comparisons

Analytical Hierarchy Process
Pairwise Comparison Matrix
A pairwise comparison matrix summarizes the pairwise
comparisons for a criteria.
Customer Market
Site A B C
A 1 3 2
B 1/3 1 1/5
C 1/2 5 1
Income Level Infrastructure Transportation
A
é 1 ùú
ê1 6 3ú
é
ê 1 1 1 ùú é
ê 1 1 1 ù
B ê ê 3 ú ê 3 2 úú
ê ú ê ú ê ú
ê1 1 1 ú ê 3 1 7 ú ê 3 1 4 ú
C ê 6
ê
9ú
ú
ê ú ê ú
ê 1 ú ê 1 ú
ê
ê
3 9 1 ú
ú
ê 1 7
1 ú ê 2 4
1 ú
ë û ëê ûú ëê ûú
Analytical Hierarchy Process
Developing Preferences Within Criteria (1 of 3)
In synthesization, decision alternatives are prioritized within each
criterion
Customer Market
Site A B C
A 1 3 2
B 1/3 1 1/5
C 1/2 5 1
11/6 9 16/5

Customer Market
Site A B C
A 6/11 3/9 5/8
B 2/11 1/9 1/16
C 3/11 5/9 5/16
Analytical Hierarchy Process
Developing Preferences Within Criteria (2 of 3)
The row average values represent the preference vector

Table 9.2 The normalized matrix with row averages

Analytical Hierarchy Process
Developing Preferences Within Criteria (3 of 3)
Preference vectors for other criteria are computed similarly,
resulting in the preference matrix

Table 9.3 Criteria preference matrix

Analytical Hierarchy Process
Ranking the Criteria (1 of 2)
Pairwise Comparison Matrix:
Criteria Market Income Infrastructure Transportation
Market 1 1/5 3 4
Income 5 1 9 7
Infrastructure 1/3 1/9 1 2
Transportation 1/4 1/7 1/2 1

Table 9.4 Normalized matrix for criteria with row averages

Analytical Hierarchy Process
Ranking the Criteria (2 of 2)

Preference Vector for Criteria:

Market
é
ê 0.1993 ùú
ê ú

Income
ê
ê 0.6535 úú
ê ú
ê ú
Infrastructure ê 0.0860 ú
ê ú
ê ú
Transportation ê
ë
0.0612 ú
û
Analytical Hierarchy Process
Developing an Overall Ranking

Overall Score:

Site A score = .1993(.5012) + .6535(.2819) + .0860(.1790) + = .3091

.0612(.1561)
Site B score = .1993(.1185) + .6535(.0598) + .0860(.6850) + = .1595
.0612(.6196)
Site C score = .1993(.3803) + .6535(.6583) + .0860(.1360) = .5314
+.0612(.2243)

Overall Ranking: Site Score

Charlotte 0.5314
Atlanta 0.3091
Birmingham 0.1595
1.0000
Analytical Hierarchy Process
Summary of Mathematical Steps
1. Develop a pairwise comparison matrix for each decision alternative for each
criteria.
2. Synthesization
a. Sum each column value of the pairwise comparison matrices.
b. Divide each value in each column by its column sum.
c. Average the values in each row of the normalized matrices.
d. Combine the vectors of preferences for each criterion.
3. Develop a pairwise comparison matrix for the criteria.
4. Compute the normalized matrix.
5. Develop the preference vector.
6. Compute an overall score for each decision alternative
7. Rank the decision alternatives.
Scoring Model Overview

Each decision alternative is graded in terms of how well it satisfies

the criterion according to following formula:
Si = Sgijwj
where:
wj = a weight between 0 and 1.00 assigned to criterion j;
1.00 important, 0 unimportant;
sum of total weights equals one.
gij = a grade between 0 and 100 indicating how well alternative
i satisfies criteria j;
100 indicates high satisfaction, 0 low satisfaction.
Scoring Model
Example Problem
Mall selection with four alternatives and five criteria:
Grades for Alternative (0 to 100)
Weight
Decision Criteria (0 to 1.00) Mall 1 Mall 2 Mall 3 Mall 4
School proximity 0.30 40 60 90 60
Median income 0.25 75 80 65 90
Vehicular traffic 0.25 60 90 79 85
Mall quality, size 0.10 90 100 80 90
Other shopping 0.10 80 30 50 70
S1 = (.30)(40) + (.25)(75) + (.25)(60) + (.10)(90) + (.10)(80) = 62.75
S2 = (.30)(60) + (.25)(80) + (.25)(90) + (.10)(100) + (.10)(30) = 73.50
S3 = (.30)(90) + (.25)(65) + (.25)(79) + (.10)(80) + (.10)(50) = 76.00
S4 = (.30)(60) + (.25)(90) + (.25)(85) + (.10)(90) + (.10)(70) = 77.75

Mall 4 preferred because of highest score, followed by malls 3, 2, 1.

Copyright © 2013 Pearson Education, Inc. Publishing as
Prentice Hall
Ranking method
Ranking method
Ranking method
Ranking method
Ranking Method
Sequel Elimination