Analytical Hierarchy Process (AHP)

Multi-criteria Decision Making

Lecture-10

1
Analytic Hierarchy Process

The Analytic Hierarchy Process (AHP), is a procedure

designed to quantify managerial judgments of the
relative importance of each of several conflicting
criteria used in the decision making process.

2
Case Study

While you are working as an active team member in PMO of a

construction company. You help senior management deciding new
business. Owing to rise in awareness among masses of projects
and people’s demand of higher life standards has brought an
opportunity of more projects. Your organization has sighted 3
projects, Project A is road project, Project B is high-rise building
and Project C is mass transit bus service lane in urban city. You
have to choose only one project based on three parameters,
i.e. profitability, technical knowledge available with your company
and client’s reputation.

3
Case Study

The project C has 100 million profit, project A has 80 million profit
and project B has 40 Million profit. Your company has full
experience in road sector, few projects in buildings and no project in
mass transit bus lane, though you have hired a new project
manager who has vast experience in that. Client for project B is
very reliable, client for project C is very ambitious and may have
some loss of support during the course of work one and client for
project A is challenging. Guidelines from top management are that
you have to go for maximum profitability and then the client’s
attitude should be considered whereas technical know-how can be
acquired from market;
Find out which project is acceptable and less risky?
4
Analytic Hierarchy Process

Step 1: List the Overall Goal, Criteria, and Decision Alternatives.

5
 Project Selection Model
 Hierarchy for the Project Selection Problem

Best Project
Overall Goal Alternative

Technical Client's
Criteria Profitability
Knowledge Reputation

Project A: Project A: Project A:

Road Project Road Project Road Project

Project B: Project Project

Decision High Rise
Building
B: High
Rise
B: High
Rise
Alternatives Project C:
Building
Project C:
Building
Project C:
Mass Transit Bus Mass Transit Bus Mass Transit Bus
Service Service Service

6
Analytic Hierarchy Process

Step 2: Develop a Pairwise Comparison Matrix

Rate the relative importance between each pair of decision alternatives.
The matrix lists the alternatives horizontally and vertically and has the
numerical ratings comparing the horizontal (first) alternative with the
vertical (second) alternative.
Ratings are given as follows:
Compared to the second alternative, the first alternative is: Numerical rating:
extremely preferred 9
very strongly preferred strongly preferred 7
moderately preferred 5
equally preferred 3
1
7
 Analytic Hierarchy Process

Step 2: Pairwise Comparison Matrix (continued)

Intermediate numeric ratings of 8, 6, 4, 2 can be assigned. A
reciprocal rating (i.e. 1/9, 1/8, etc.) is assigned when the
second alternative is preferred to the first. The value of 1 is
always assigned when comparing an alternative with itself.

Compared to the second alternative, the first alternative is: Numerical rating:
extremely preferred to very strongly preferred 8
very strongly preferred to strongly preferred 6
strongly preferred to moderately preferred 4
moderately preferred to equally preferred 2
8
Pairwise Comparison Matrix:
Profitability

The project C has 100 million profit, project A has 80 million

profit and project B has 40 Million profit.
Team has decided that in terms of profitability, Project C is
moderately preferred to Project A and very strongly preferred
to Project B. In turn Project A is strongly to very strongly
preferred to Project B.

9
Pairwise Comparison Matrix:
Profitability

Project A Project B Project C

Project A 6

Project B

Project C 3 7

10
Pairwise Comparison Matrix:
Profitability

Project A Project B Project C

Project A 1 6 1/3

Project B 1/6 1 1/7

Project C 3 7 1

11
Pairwise Comparison Matrix:
Profitability

Project A Project B Project C

Project A 1 6 1/3

Project B 1/6 1 1/7

Project C 3 7 1

12
Analytic Hierarchy Process

Step 3: Develop a Normalized Matrix

Divide each number in a column of the pair wise comparison

matrix by its column sum.

13
 Normalized Matrix: Profitability

Divide each entry in the pairwise comparison matrix by its

corresponding column sum.

Project A Project B Project C

Project A 1 6 1/3

Project B 1/6 1 1/7

Project C 3 7 1

4.17 14 1.48

14
Normalized Matrix: Profitability

For example, for Project A the column sum = 1 + 3 + 1/6 = 25/6 or

4.17. This gives (like 1 / 4.17 = 0.24)

Project A Project B Project C

Project A 0.24 0.43 0.23

Project B 0.04 0.07 0.10

Project C 0.72 0.50 0.68

15
Analytic Hierarchy Process

Step 4: Develop the Priority Vector

Average each row of the normalized matrix. These row

averages form the priority vector of alternative preferences with
respect to the particular criterion. The values in this vector sum
to 1.

16
Priority Vector: Profitability

The priority vector is determined by averaging the row entries in the

normalized matrix. Converting to decimals we get:

Project A: (0.24+0.43+0.23)/3 = .298

Project B: (0.04+0.07+0.10)/3 = .069
Project C: ( 0.72+0.50+0.68)/3 = .632

17
Analytic Hierarchy Process

Step 5: Calculate a Consistency Ratio

The consistency of the subjective input in the pairwise comparison

matrix can be measured by calculating a consistency ratio. A
consistency ratio of less than 0.1 is good. For ratios which are
greater than 0.1, the subjective input should be re-evaluated.

Consistency Ratio: CR = CI/RI

where CI = Consistency Index
RI = Random Index
------For each criterion, perform steps 2 through 5------
------- 18
Determining the Consistency Ratio

Step 1: For each row of the pairwise comparison matrix, determine a

weighted sum by summing the multiples of the entries by the
priority of its corresponding (column) alternative.
Step 2: For each row, divide its weighted sum by the priority of its
corresponding (row) alternative.
Step 3: Determine the average,  max, of the results of step 2.

19
Determining the Consistency Ratio

Step 4: Compute the consistency index, CI, of the n alternatives by: CI = (max -
n)/(n - 1).

Step 5: Determine the random index, RI, as follows:

Number of Random Index Number of Random Index

Alternative (n) (RI) Alternative (n) (RI)

3 0.58 6 1.24
4 0.90 7 1.32
5 1.12 8 1.41

Step 6: Compute the consistency ratio: CR = CI/RI.

18
Checking Consistency

Multiply each column of the pairwise comparison matrix by its priority:

1 6 1/3 0.922
.298 1/6 + .069 1 + .632 1/7 = 0.209
3 7 1 2.009

21
Checking Consistency

Multiply each column of the pairwise comparison matrix by its priority:

.298 .414 .210 0.922

.049 + .069 + .091 = 0.209
.894 .483 .632 2.009

22
Checking Consistency

Divide each result by its priority to get:

0.922/0.298 = 3.09
0.209/0.069 = 3.02
2.009/0.632 = 3.18

23
Checking Consistency

Average the above results to get λmax.

λmax = (3.09 + 3.03 + 3.18)/3 = 3.10

Compute the consistence index, CI, for three terms (n = 3).

CI = (λmax - n)/(n - 1) = (3.10 - 3)/2 = 0.05

Compute the consistency ratio, CR, by CI/RI, where RI = .58 for 3 factors:
CR = CI/RI = 0.05 /.58 = 0.086
Since the consistency ratio, CR, is less than .10, this is well within the acceptable
range for consistency.
24
Pairwise Comparison Matrix:
Technical Knowledge

Your company has full experience in road sector, few projects in

buildings and no project in mass transit bus lane, though you have
hired a new project manager who has vast experience in that.

Team has decided that in terms of Technical Knowledge, Project A is

Strongly preferred to Project B and extremely preferred to
Project C. In turn Project B is very strongly preferred to Project C.

25
Pairwise Comparison Matrix:
Technical Knowledge

Project A Project B Project C

Project A 5 9

Project B 7

Project C

26
Pairwise Comparison Matrix:
Technical Knowledge

Project A Project B Project C

Project A 1 5 9

Project B 1/5 1 7

Project C 1/9 1/7 1

27
Pairwise Comparison Matrix:
Technical Knowledge

Project A Project B Project C

Project A 1 5 9

Project B 1/5 1 7

Project C 1/9 1/7 1

28
Normalized Matrix: Technical Knowledge

Divide each entry in the pairwise comparison matrix by its corresponding

column sum.

Project A Project B Project C

Project A 1 5 9

Project B 1/5 1 7

Project C 1/9 1/7 1

1.31 6.14 17
29
Normalized Matrix: Technical
Knowledge
Divide each entry in the pairwise comparison matrix by its
corresponding column sum.

Project A Project B Project C

Project A 0.76 0.81 0.53

Project B 0.15 0.16 0.41

Project C 0.08 0.02 0.06

30
Priority Vector: Technical Knowledge

The priority vector is determined by averaging the row entries in

the normalized matrix. Converting to decimals we get:

Project A: (.76+.81+.53)/3 = .70

Project B: (.15+.16+.41)/3 = .24
Project C: ( .08+.02+.06)/3 = .05

 Checking Consistency
Company’s responses to Technical Knowledge could be checked for
consistency in the same manner as was cost.
31
Pairwise Comparison Matrix: Client

Client for project B is very reliable, client for project C is very

ambitious and may have some loss of support during the course of
work one and client for project A is challenging.

Team has decided that in terms of Client’s Reputation, Project B is

Strongly preferred to Project C and very strongly preferred to
Project A. In turn Project C is moderately preferred to Project A.

32
Pairwise Comparison Matrix: Client

Project A Project B Project C

Project A

Project B 7 5

Project C 3

33
Pairwise Comparison Matrix: Client

Project A Project B Project C

Project A 1 1/7 1/3

Project B 7 1 5

Project C 3 1/5 1

34
Normalized Matrix: Client

Project A Project B Project C

Project A 1 5 9

Project B 1/5 1 7

Project C 1/9 1/7 1

11 1.34 6.33
35
Normalized Matrix: Client

Divide each entry in the pairwise comparison matrix by its

corresponding column sum.
Project A Project B Project C

Project A 0.09 0.11 0.05

Project B 0.64 0.74 0.79

Project C 0.27 0.15 0.16

36
Priority Vector: Client

The priority vector is determined by averaging the row entries in

the normalized matrix. Converting to decimals we get:

Project A: (.09+.11+.05)/3 = .083

Project B: (.64+.74+.79)/3 = .723
Project C: (.27+.15+.16)/3 = .193

 Checking Consistency
Company’s responses to Client Reputation could be checked for consistenc
the same manner as was cost.
37
Pairwise Comparison Matrix: Criteria

Guidelines from top management are that you have to go for

maximum profitability and then the client’s attitude should be
considered whereas technical knowhow can be acquired from
market.

Team has decided that in terms of Criteria, Profitability is Strongly

preferred to Client Attitude and extremely preferred to Technical
Knowledge. In turn Client’s Attitude is moderately preferred to
Technical Knowledge.

38
Pairwise Comparison Matrix: Criteria

Technical
Profitability Client Knowledge

Profitability 5 9

Client 3

Technical
Knowledge

39
Pairwise Comparison Matrix: Criteria

Technical
Profitability Client Knowledge

Profitability 1 5 9

Client 1/5 1 3

Technical
Knowledge 1/9 1/3 1

40
Normalized Matrix: Criteria

Divide each entry in the pairwise comparison matrix by its

corresponding column sum.
Technical
Profitability Client
Knowledge

Profitability 1 5 9

Client 1/5 1 3

Technical
1/9 1/3 1
Knowledge

1.31 6.33 13

41
Normalized Matrix: Criteria

Divide each entry in the pairwise comparison matrix by its

corresponding column sum.
Technical
Profitability Client Knowledge

Profitability 0.76 0.79 0.69

Client 0.15 0.16 0.23

Technical
Knowledge 0.08 0.05 0.08

42
Priority Vector: Criteria

The priority vector is determined by averaging the row entries in

the normalized matrix. Converting to decimals we get:

Profitability: (0.76+0.79+0.69)/3 = .74

Client: (0.15+0.16+0.23)/3 = .18
Technical Knowledge: (0.08+0.05+0.08)/3 = .07

43
Analytic Hierarchy Process

Step 6: Develop a Priority Matrix

After steps 2 through 5 has been performed for all criteria,

the results of step 4 are summarized in a priority matrix by
listing the decision alternatives horizontally and the criteria
vertically. The column entries are the priority vectors for
each criterion.

44
 Priority Vector:
Overall Priority Vector Criteria

Priority Vector:
Profitability

Priority Vector:
Client’s Attitude

Priority Vector:
Technical Knowledge

45
Overall Priority Vector

The overall priorities are determined by multiplying the priority vector of the
criteria by the priorities for each decision alternative for each objective.

Priority Vector
[ 0 .74 0.18
for Criteria 0.07 ]
Technical
Profitability Client
Knowledge

Project A 0.30 0.083 0.70

Project B 0.07 0.73 0.24

Project C 0.63 0.19 0.05

46
Analytic Hierarchy Process

Step 7: Develop a Criteria Pairwise Development Matrix

This is done in the same manner as that used to construct alternative
pairwise comparison matrices by using subjective ratings (step 2).
Similarly, normalize the matrix (step 3) and develop a criteria priority
vector (step 4).

Step 8: Develop an Overall Priority Vector

Multiply the criteria priority vector (from step 7) by the
priority matrix (from step 6).
47
Overall Priority Vector

Thus, the overall priority vector is:

Project A: (.74)(.30) + (.18)(.083) + (.07)(.70) = .286

Project B: (.74)(.07) + (.18)(.72) + (.07)(.24) = .198
Project C: (.74)(.63) + (.18)(.19) + (.07)(.05) = .504

As we can see from the Table that the highest score(0.504) is of "Project C" i-e
Mass Transit Bus Service Lane. So, this project appears to be the overall
recommendation.

48
Overall Priority Vector

Thus, the overall priority vector is:

Project A: (.74)(.30) + (.18)(.083) + (.07)(.70) = .286

Project B: (.74)(.07) + (.18)(.72) + (.07)(.24) = .198
Project C: (.74)(.63) + (.18)(.19) + (.07)(.05) = .504

As we can see from the Table that the highest score(0.504) is of "Project C" i-e
Mass Transit Bus Service Lane. So, this project appears to be the overall
recommendation.

49
Summary of This Lecture

In this Lecture, we have discussed about

 Definition of AHP & Use of AHP in decision making

 AHP Process
 Goal, Criteria & Alternative listing
 Pair wise Comparison matrix
 Develop a normal matrix
 Develop the priority vector
 Calculate consistency ratio
 Develop a priority matrix
 Develop an overall priority vector 40
Assignment - 2

Watch the YOUTUBE documentary on “The Deepwater Horizon Oil Spill

in the Gulf of Mexico” by FRONTLINE available on the link given below:

https://www.youtube.com/watch?v=NzrGZCJojUE

 Followings Questions to answer are required to submit from the above

documentary content:
1. What are the Major Risks BP were avoiding and how they impact later to the
Company?
2. Who raised the voice against the potential risks/threats and what are they?
3. What are the primary, secondary, emergent and residual risks identified in the
incidents that happened in the documentary?
 END NOTE

“ The greatest Discovery of our

generation is that a human being can
alter his life by altering his attitudes”
- William James

52
THANKS!
Any question?

53