Multi-Criteria Decision Analysis Tools

2022-06-30
 Multi-Criteria Decision
Analysis (MCDA)

1
 Multi-Criteria Decision Analysis Tools

• Multi-criteria decision analysis (MCDA) is a formal, structured and

transparent decision-making methodology.
• Its aim is to assist groups or individual decision-makers to explore their
decisions in the case of complex situations with multiple criteria.

• MCDA assists the decision-maker in confidently reaching a decision by:

• Enabling decision-makers to gain a better understanding of the problem faced;
• Organizing and synthesizing the entire range of information;
• Integrating objective measurements with value judgments;
• Making explicit and managing the decision maker’s subjectivity; and
• Ensuring that all criteria and decision factors have been taken properly into account

第 3 页
 MCDA

• MCDA is an umbrella term for a range of tools and methodologies.

• The level of complexity, interaction with the decision-maker and level of detail utilized in
the decision-making process can vary substantially.

In general, the decision-maker follows the same process: 

1. Identify multiple criteria on which to base their decision;
2. Identify multiple alternative solutions to their decision;
3. Provide (subjective) ranking or weighting of criteria; and
4. Provide values, rankings or weighting of alternatives for each criterion.

第 4 页
 Analytical Hierarchy Process
(AHP)
2

2
 AHP

• AHP was developed in the late 1970s. Today it is the most widely used MCDA method.

• Allows the use of qualitative, as well as quantitative criteria in evaluation.

• AHP generates all criteria weighting and alternative preferences within each criterion by eliciting these
values from the decision-maker through a series of pairwise comparisons instead of using numerical
values directly.

• Thus, a complex decision is reduced to a series of simpler ones, between pairs of alternative values
within criteria or between pairs of criteria.
• However, it is essential to generate an optimized hierarchy of criteria and alternatives, to reduce the
number of pairwise decisions.

第 6 页
 AHP

• AHP algorithm is basically composed of two steps:

1. Determine the relative weights of the decision criteria
2. Determine the relative rankings (priorities) of alternatives

Step 0: Construction of Hierarchy Structure

(including Goal, Factors, Criteria, and Alternatives)
Step 1: Calculation of Factor Weight
Step 1-1: Pairwise Comparison Matrix
Step 1-2: Eigenvalue and Eigenvector (Priority vector)
Step 1-3: Consistency Test
Consistency Index
Consistency Ratio
Step 2: Calculation of Level Weight

Step 3: Calculation of Overall Ranking

第 7 页
AHP

Hierarchy Tree
Level 0 Goal More General

Level 1 (factors) C1 C2 C3

C11 C12 C13 C21 C22 C31 C32 C33

Level 2 (criteria)

Sub-criteria at the More Specific

lowest level

Level ..n Alternatives

第 8 页
 AHP

Ranking Scale for Criteria and Alternatives

Relative
Importance of criterion
importance
1 Equal importance
3 Moderate importance
Values 2,4,6,8
5 Strong importance intermediate values
7 Very strong importance
9 Absolute importance

第 9 页
 AHP

• The pair-wise comparison matrix ), is determined for all decision criteria where is the total number of criteria.

• Every element indicates the comparative importance of parameter with respect to parameter .

• The indicates the importance of criteria to criteria , indicates and , indicates the reciprocal importance of criteria
relative to criteria i.

[ ]
1 𝑎12 … 𝑎1 𝑛
𝑎 21 1 … 𝑎2 𝑛
A= 𝑎 𝑗𝑖 =1 / 𝑎 𝑖𝑗 , 𝑎𝑖𝑗 ≠ 0
… … … …
𝑎𝑛 1 𝑎𝑛 2 … 1

第 10 页
 AHP

• Once the pairwise comparison matrix is defined, calculate the relative normalized weight of
each parameter from the geometric mean of row.

( )𝑛 geometric mean of row

𝑛
G M 𝑖 → ∏ ❑𝑖=1 𝑥 𝑖

GM 𝑖 relative normalized weight of each parameter

𝑊 𝑖=
∑
𝑛
❑𝑖 = 1 GM 𝑖

第 11 页
 AHP

Example 1: Car Selection

 Goal
 Selecting a car
 Criteria
 Style, Reliability, Fuel-economy
 Alternatives
 Civic Coupe, Saturn Coupe, Ford Escort, Mazda Miata

第 12 页
 Example: Car Selection

Hierarchy tree

Civic Saturn Escort Miata

第 13 页
 Example: Car Selection

Ranking of Criteria

Style Reliability Fuel Economy

Style 1 1/2 3

Reliability 2 1 4

Fuel Economy 1/3 1/4 1

第 14 页
 Example: Car Selection

Ranking of Priorities
 Consider [Ax =  x] where
 A is the comparison matrix of size n×n, for n criteria, also called the priority matrix.

 x is the Eigenvector of size n×1, also called the priority vector.

  is the Eigenvalue,   > n.

 To find the ranking of priorities, namely the Eigen Vector X:

1) Normalize the column entries by dividing each entry by the sum of the column.
2) Take the overall row averages.

Pairwise Comp. Matrix Norm. Pairwise Comp. Matrix Priority vector

Normalized Row
1 0.5 3 0.30 0.29 0.38 0.3196
Column Sums Averages
A= 2 1 4 0.60 0.57 0.50 0.5584
X=
0.33 0.25 1.0 0.10 0.14 0.13 0.1220

Column sums 3.33 1.75 8.00 1.00 1.00 1.00

第 15 页
 Example: Car Selection

Ranking of Priorities
Criteria weights
• Style 0.3196 ≈ 0.3 Second most important criterion

• Reliability 0.5584 ≈ 0.6 First important criterion

• Fuel Economy 0.1220 ≈ 0.1 The least important criterion

The tree of criteria with the criteria weights

第 16 页
 Example: Car Selection

Calculation of Consistency Ratio

 The next stage is to calculate , Consistency Index (CI) and the Consistency Ratio
(CR).
ts
 Consider [Ax = x] where x is the Eigenvector.
eig h
w
A x ria Ax x
ir te
C
1 0.5 3 0.30 0.90 0.30
2 1 4 0.60 = 1.60 =  0.60
0.10 0.35 0.10
0.333 0.25 1.0
0.90/0.30 3.00
 Consistency Vector = 1.60/0.60 = 2.67
0.35/0.10 3.50
 Consistency index (CI) is given by

第 17 页
 Example: Car Selection

Ranking Alternatives Selecting a New Car

1.00

Style Reliability Fuel Economy

0.30 0.60 0.10
Civic 0.13 Civic 0.38 Civic 0.30
Saturn 0.24 Saturn 0.29 Saturn 0.24
Escort 0.07 Escort 0.07 Escort 0.21
Miata 0.56 Miata 0.26 Miata 0.25

Car Style(0.3) Reliability(0.6) Fuel Economy(0.1) Total

Civic 0.13 0.38 0.30 0.30

Saturn 0.24 0.29 0.24 0.27
Escort 0.07 0.07 0.21 0.08 Mazda Miata
Miata 0.56 0.26 0.25 0.35 largest 第 18 页
Thank You!
Yonas A.
2022-06-23