Geoinformatic For

Disaster Management
(ESC5519)
Multicriteria Decision
Making Analysis (MCDA):
Analytical Hierarchy Processes (AHP)

[email protected] | www.forenv.upm.edu.my
What is Decision
Analysis?
Why do we use it?
 Typical Decision-Making
Challenges
Humans are quite bad at making complex,
unaided decisions (Slovic et al., 1977).
• A variety of psychological biases tend to skew our
rationality.
• We can only keep a few factors in ‘working memory’
at a time, so are liable to miss considerations without
decision aids.
• Individuals respond to complex challenges by using
intuition and/or personal experience to find the
easiest solution.
 Approaches to Evaluation

Subjective Prioritization (“Gut Feeling”)

• Pros: easy to do
• Cons: no rigor, potential mistakes, poor transparency/reliability
Ad hoc weighting using Excel Spreadsheets
• Pros: everybody can use Excel, relative ease of implementing
• Cons: requires arbitrary weighting for multiple criteria, ad hoc metrics, etc.
Decision Analysis
• Pros: transparent, state-of-the-art methods, can be tailored/modified in real
time, records and visualizes differences among commands and individual
opinions.
• Cons: time and resource intensive, potentially costly, expertise required.
 Decision Analysis
Provides frameworks for comparing data for
alternatives across dissimilar criteria.

Facilitates making relative tradeoffs between criteria

of different importance.

Normalizes data context of decision at hand.

Aggregates across criteria to prioritize alternatives.

 Multi-Criteria Decision Analysis
MCDA:
• Evolved as a response to the observed
inability of people to effectively analyze
multiple streams of dissimilar
information
• Has many different technical
approaches based on similar theoretical
foundations
- MCDA integrates various technical
inputs & evaluations with stakeholder &
decision maker preferences/values.
- MCDA allows you to ask the right people
for right info.
- MCDA methods show why a particular
alternative is most valued.
- MCDA allows you to explore impact of
scenario/data uncertainty and value of
reducing it.
 Summary of MCDA Benefits
Some benefits of implementing formal decision analysis:
• Transparent – always clear how and why each item is scored.
• Replicable – anybody will receive the same answer.
• Generalizable – methods are easily ported between contexts.
• Robust – there is a science behind this that we can leverage.
• Tractable – break large problems down to focus on like parts.
• Scalable – decision framework can be applied to large data.
• Quantitative – easier to justify outcomes to ‘higher-ups’.
• Helps you identify the full set of objectives for the analysis.
• Allows exploration of trade-offs between these objectives.
• Separates subjective (weights) from objective (scores) data.
• Can integrate values across a group with diverse views.
 Methods
Several methods are commonly used in Multi-Criteria Decision Analysis
(MCDA) to support decision-making processes. Here are a few commonly
employed techniques:
1.Weighted Sum Model: This method involves assigning weights to each
criterion based on relative importance and then calculating a weighted sum
for each alternative. The alternative with the highest weighted sum is
considered the most favorable.
2.Analytic Hierarchy Process: decomposes complex decisions into a
hierarchical structure of criteria and sub-criteria. Decision-makers make
pairwise comparisons between criteria to derive their relative priorities,
which are then used to calculate overall scores for alternatives.
3.Technique for Order Preference by Similarity to Ideal Solution: It
measures the relative proximity of each alternative to an ideal solution and
a worst-case solution. The best choice is the alternative with the shortest
distance to the ideal solution and the greatest distance to the worst-case
solution.
 Decision Analysis in Disaster
Management
Decision analysis is crucial in the field of disaster management for
several reasons. Disasters, whether natural or human-made, pose
significant challenges that require effective and informed
decision-making.
• Resource Allocation: Limited resources, such as personnel, equipment, and funds, are
common challenges in disaster management. Decision analysis helps in optimizing resource
allocation by assessing priorities and identifying the most efficient and effective strategies. This
ensures that resources are utilized where they are needed the most.

• Risk Assessment: Decision analysis facilitates the assessment of risks associated with
different courses of action. By evaluating the potential consequences of various decisions,
decision-makers can make informed choices that minimize negative impacts and enhance the
overall resilience of the community.

• Stakeholder Involvement: Disaster management involves multiple stakeholders, including

government agencies, non-governmental organizations, and the local community. Decision
analysis provides a framework for involving stakeholders in the decision-making process. This
inclusiveness helps in considering diverse perspectives and ensures that decisions are well-
informed and supported by those affected.
 The Analytic
Hierarchy
Process (AHP)
 Overview of AHP
• The Analytic Hierarchy Process (AHP) is a method for
organizing and analyzing complex decisions, using
math and psychology. It was developed by Thomas L.
Saaty in the 1970s.
• It contains three parts: the ultimate goal or problem
you’re trying to solve, all of the possible solutions,
called alternatives, and the criteria you will judge the
alternatives on. AHP provides a rational framework for
a needed decision by quantifying its criteria and
alternative options, and for relating those elements to the
overall goal.
 Examples
• Buying a house
– Cost, proximity of schools, trees, nationhood,
public transportation
• Buying a car
– Price, interior comfort, mpg, appearance, etc.
• Going to a college
Demonstrating AHP Technique
• Identified three potential location alternatives: A,
B, and C
• Identified four criteria: Market, Infrastructure,
Income level, and Transportation
• 1st level: Goal (select the best location)
• 2nd level: How each of the 4 criteria contributes
to achieving objective
• 3rd level: How each of the locations contributes
to each of the 4 criteria
General Mathematical Process
• Establish preferences at each of the levels
– Determine our preferences for each location for
each criteria
• A might have a better infrastructure over the other
two
– Determine our preferences for the criteria
• which one is the most important
– Combine these two sets of preferences to
mathematically derive a score for each location
 Pairwise Comparisons
Preference Level Numerical
• Used to score each Value
alternative on a Equally preferred 1
criterion. Equally to moderately 2
preferred
• Compare two Moderately preferred 3
alternatives Moderately to strongly 4
according to a preferred
criterion and Strongly preferred 5
indicate the Strongly to very strongly 6
preference using a preferred
Very strongly preferred 7
preference scale.
Very strongly to extremely 8
• Standard scale preferred
used in AHP. Extremely preferred 9
 Pairwise Comparison
• If A is compared with B
for a criterion and
preference value is 3,
then the preference value
of comparing B with A is
1/3.
• Pairwise comparison
ratings for the market
criterion.
• Any location compared to Market
itself, must equally location A B C

preferred. A 1 3 2
B 1/3 1 1/5
C 1/2 5 1
 Other Pairwise Comparison
Market Income level
location A B C location A B C
A 1 3 2 A 1 6 1/3
B 1/3 1 1/5 B 1/6 1 1/9
C 1/2 5 1 C 3 9 1

Infrastructure Transportation
location A B C location A B C
A 1 1/3 1 A 1 1/3 1/2
B 3 1 7 B 3 1 4
C 1 1/7 1 C 2 1/4 1
 Developing Preferences within Criteria
Market
• Prioritize the decision location A B C
alternatives within each A 1 3 2
criterion
B 1/3 1 1/5
• Divide each entry by the C 1/2 5 1
total of its column. Market
• Notice how the columns location A B C
add up to approximately A 1 3 2
1.0. This is because the B 0.33 1 0.2
weights have now been C 0.5 5 1
standardized. Total 1.83 9 3.2

This weighted score suggests the following:

Market

location A B C Average • Location A represents about 50% of

the final decision
A 0.55 0.33 0.63 0.50 • Location B represents about 12% of
the decision
B 0.18 0.11 0.06 0.12
• Location C represents about 38% of
C 0.27 0.55 0.31 0.38 the decision
 Other Preference Vectors
Location Market Income Level Infrastructure Transportation

A 0.5012 0.2819 0.1780 0.1561

B 0.1185 0.0598 0.6850 0.6196

C 0.3803 0.6583 0.1360 0.2243

 Ranking the Criteria

Transportation
infrastructure
Income
Market
• Determine the relative Criteria

importance or weight of the

criteria Market 1 1/5 3 4
– which one is the most Income 5 1 9 7
important and which one is the
least important one infrastructure 1/3 1/9 1 2

• Accomplished the same way Transportation 1/4 1/7 1/2 1

we ranked the locations within

each criterion, using pairwise
comparison.
 Normalizing

Transportation
Infrastructure

Average
Income
Market
Criteria

Market 0.1519 0.1375 0.2222 0.2857 0.1993

Income 0.7595 0.6878 0.6667 0.5000 0.6535

Infrastructure 0.0506 0.0764 0.0741 0.1429 0.0860

Transportation 0.0380 0.0983 0.0370 0.0714 0.0612

Income level is the highest priority criterion followed by market

 Developing Overall Ranking

Transportation
Income Level

Infrastructure
Location

Average
Market
Criteria

A 0.5012 0.2819 0.1780 0.1561 Market 0.1993

B 0.1185 0.0598 0.6850 0.6196
Income 0.6535
C 0.3803 0.6583 0.1360 0.2243

Infrastructure 0.0860
Overall Score A= (0.1993)(0.5012)+(0.6535)(0.2819)+ Transportation 0.0612
(0.1780)(0.0860)+(0.1561)(0.0612)
=0.3091 Preference Vector
Overall Score B =0.1595
Overall Score C =0.5314
Location C is the clear winner! You can
interpret this to mean that Location C
meets 53% of all the decision criteria
considered. Location A meets only 31%
of the criteria, and Location B meets
15%.
 Summary
• Develop a pairwise comparison matrix for each decision
alternative for each criterion
• Synthesization
– Sum values in each column
– Divide each value in each column by the corresponding column
sum
– Average the values in each row (provides preference vector for
decision alternatives)
– Combine the preference vectors
• Develop the preference vector for criteria in the same
way
• Compute an overall score for each decision alternative
• Rank the decision alternatives
 Exercise
• Purchasing a mountain bike
II-Gear Action
• Three criteria: price, gear
Bike A B C
action, weight/durability
A 1 1/3 1/7
• Three types of bikes: A,B,C
B 3 1 1/4
• Developed pairwise
comparison matrices I,II,III C 7 4 1
• Ranked the decision criteria
based on the pairwise III-Weight/Durability
comparison
Bike A B C
• Select the best bike using AHP
A 1 3 1

B 1/3 1 1/2

C 1 2 1

I-Price
Criteria Price Gear Weight
Bike A B C
Price 1 3 5
A 1 3 6
B 1/3 1 2 Gear 1/3 1 2
C 1/6 2 1 Weight 1/5 1/2 1
 Conclusion
• Decision Analytic approaches represent the practical
application of analytical tools to support complex
decisions, allocation problems and planning processes.
• Benefits include transparency, flexibility, repeatability
between decision makers, and responsiveness to
multiple planning scenarios.
• Applications are diverse but all require decision maker /
stakeholder consideration of multiple criteria/alternatives.
• This can
1) help with integration of methods in tools, and
2) implement some ‘default’ decision models for cases.
Thank you
www.upm.edu.my