Decision Analysis

Advanced Topics PM
Spring 2024

Multicriteria Decision Making

AHP - Analytic Hierarchy Process

Decision Analysis

Analytical Hierarchy Process (AHP)

Overview
A method for ranking several decision alternatives and
selecting the best one when there are multiple objectives,
or criteria, on which to base the decision.
Make a decision based on how the alternatives compare
according to several criteria.
Select the alternative that best meets the decision criteria.
AHP is a process for developing a numerical score to rank
each decision alternative based on how well the alternative
meets the decision maker’s criteria.

22
 Decision Analysis

Analytical Hierarchy Process (AHP)

• A way to structure decision problem
• Used to prioritize alternatives
• Attempts to mirror human decision process
• Easy to use & well accepted by decision makers
– Used often - familiarity
– Intuitive
• Can be used for multiple decision makers

Decision Analysis

AHP Procedure – Build the Hierarchy

• A hierarchical structure
– Goal on top (Fundamental Objective)
– Decompose into sub-goals (Means objectives)
– Further decomposition as necessary
– Identify criteria (attributes) to measure
achievement of goals (attributes and objectives)

4
 Decision Analysis

Decision Analysis
Decision Example
I want to buy an MP3 player. I have the choice of colors (pink,
blue, green, black, red), storage (8, 16, 32, 64 GB), and
availability (immediate, 1 week, 1 month).

6
 Decision Analysis
Example: Buying a Car

AHP uses pairwise comparisons. Two alternatives are

compared according to a criterion and one is preferred.
compare purchase cost with maintenance cost

Decision Analysis
Analytical Hierarchy Process
Pairwise Comparisons

Preference Scale for Pairwise Comparisons

88
 Decision Analysis
How to assign Numerical Criteria A Criteria B

and Reciprocal ratings Criteria A

Criteria B

Use odd numbers from

the table to ensure a
reasonable distinction
among the measurement
points.

Use even numbers only if

there is a need for
negotiation between the
evaluators.

Decision Analysis

Example - Pairwise Comparisons

• Consider following criteria
Purchase Cost Maintenance Cost Gas Mileage

• Want to find weights on these criteria

• AHP compares everything two at a time

(1) Compare Purchase Cost to Maintenance Cost

– Which is more important / preferred?

Say purchase cost
– How much? Moderately preferred 3

10
 Decision Analysis

Example - Pairwise Comparisons

(2) Compare Purchase Cost to Gas Mileage

– Which is more important / preferred?

Say purchase cost
– How much? Strongly preferred 5

(3) Compare Maintenance Cost to Gas Mileage

– Which is more important?

Say maintenance cost
– How much? Very strongly preferred 7

11

Decision Analysis

Example Scenario: Project Selection

Problem: Decision making in a complex environments in which
many criteria are considered in the prioritization and
selection of projects.
Method: Apply analytic hierarchy process (AHP) in the
prioritization and selection of projects in a portfolio.
Approach: Determine the criteria that will be used.
Each organization develops its own set of criteria, which must
be aligned to the strategic objectives of the organization.

Example problem requires project selection based

upon four criteria identified by the organization.

12
 Decision Analysis

AHP Example: Project Selection

13

Decision Analysis
• Identified criteria must be evaluated in pairs so as to
determine the relative importance between them.
• Decision makers have provided following information
showing relative preference between the criteria.

Financial is strongly preferred to Stakeholder comm. (5)

Strategic is extremely preferred to Stakeholder comm. (9)
Fill in the complete table and take column totals.
14
 Decision Analysis

Normalize the data. Divide each cell value by the column total.

16

Decision Analysis

Calculate weight of each criteria

• Priority Vector is the row average.

• Contribution of each criterion to the goal is determined
by the priority vector (or Eigenvector)
• Shows the relative weights between each criterion;

17
 Decision Analysis
Relative importance of each criteria

18

Decision Analysis

Consistency Check of the Ratings

• Ratings assigned to criteria should be consistent
(1) Ratings should be transitive
– That means that
If A is better than B
and B is better than C
then A must be better than C

(2) Ratings should be numerically consistent.

19
 Decision Analysis
Checking Consistency
Use the same matrix determined previously for the four criteria.
Calculate Priority vector (row average) for each.

20

Decision Analysis
Consistency Index and Ratio (CI & CR)

21
 Decision Analysis
Consistency Index and Ratio

Consistency index = (4.044 – 4) / (4 – 1) = 0.015

For CR, divide CI by RI value from table below for n.
Here, n = 4, so RI = 0.90 from the table.
Consistency Ratio = 0.015 / 0.90 = 0.0167
Note: CR value of less than 0.10 is okay (means ratings are consistent).

22

Decision Analysis
Comparing each project against all four criteria
one by one… Stakeholder Commitment first.

Normalizing the scores and calculating Priority Vector

23
 Decision Analysis

Criteria 1: Stakeholder Commitment

24

Decision Analysis

Criteria 2: Financial

25
 Decision Analysis

Criteria 3: Strategic

26

Decision Analysis

Criteria 4: Other Criteria

27
 Decision Analysis

Summary of Priority Vectors

Four columns in the table above correspond to the priority

vectors as calculated previously for each criteria.

Overall score is the sum.product of criteria weights with

each row.
Project A: 0.069x0.18 + 0.395x0.091 + 0.457x0.643 + 0.079x0.283 = 0.365
28

Decision Analysis
Overall Ranking

DECISION: Project C will be preferred as its priority score is

the highest.
29
 Decision Analysis

30

Decision Analysis
Practice Problem: CI and CR
Table shows relative visual
brightness of four chairs.
Determine if the ratings are
consistent by finding CI
and CR.
Chair 1 Chair 2 Chair 3 Chair 4 Priority Cons CM/PV
Vector Measure

Chair 1 1
Chair 2 1
Chair 3 1
Chair 4 1

31
 Decision Analysis

CI = (4.409 – 4) / (4 – 1) = 0.1363
CR = CI/RI = 0.1363/0.9 = 0.1514
This value is greater than 0.10 so the ratings are inconsistent.
See provided Excel sheet for calculations performed in class.
32

Decision Analysis

Exercise Problem 1
Determine the Consistency Ratio for the following ratings
matrix.

33
 Decision Analysis

Exercise Problem 2

34