You are on page 1of 20

In d u s t rial En gi n eeri n g| MARMARA UNIVERSIT Y

IE4031

DECISION ANALYSIS
Making Decisions with Multiple Objectives

Dr. Zeynep Tuğçe Kalender 05.11.2021


This video is copyrighted by Res. Asst. Dr. Zeynep Tuğçe Kalender,
Marmara University and is protected under the 5486-Law of on Intellectual
and Artistic Works (T.C. 5486 no'lu Fikir ve Sanat Eserleri Kanunu) and all
applicable international, federal, state and local laws, with all rights reserved.

No part of this may be copied, distributed, or changed in any format, sold or


used in any way other than individual learning purposes without express
permission from Res. Asst. Dr. Zeynep Tuğçe Kalender, Marmara University.
Making Decisions with Multiple Objectives

ONE OBJECTIVE AT A TIME TRADE-OFF ANALYSIS

One way to approach the analysis of a Combine multiple objectives into one
multiple-objective decision is to calculate overall objective. Multiple objectives must
the expected value or create the risk profile have comparable scales.
for each individual objective.
In d u s t rial En gi n eeri n g| MARMARA UNIVERSIT Y

CASE STUDY
Summer Job Example
Sam Chu has two job offers and he does not know which one to choose.

• The first alternative is an assistant position at a local small business.


They will pay minimum wage ($5.25 per hour), they ask 25-35 hours
of work per week, during weekdays, hence Sam will be free in
weekends. This is a summer position, lasting for 3 months, but there
is uncertainty regarding the exact amount of work, and hence the total
amount he will earn.

• The second alternative is to work as a member of a trail-maintenance


crew for a conservation organization. This job will require 10 weeks
of hard work, 40 hours per week at $6.50 per hour, in a national forest
in a neighboring state. He will have to do extensive camping and
backpacking. Members of the crew will come from a large geographic
area and spend the entire ten weeks together, including weekends. The
amount of money Sam will earn is known, but there is uncertainty
regarding the relations between Sam and the staff and other crew
members. The ten weeks period can be a wonderful time, a total
misery, or anything in between.
Sam has two objectives in this context: Earning money and having fun
for summer, and the two jobs offer different possibilities in terms of
these two objectives.

The first objective has a natural scale ($), but the second objective has no
such scale and the first step should be to define such a scale. After some
thinking and consulting Sam has prepared Table.

Level of Fun Description


5 (Best) A large congenial group of friends. Many new friendships made. Work is
enjoyable and time passes quickly.
4 A small but congenial group of friends. The work is interesting, and time off
work is spent with a few friends in enjoyable pursuits.
3 No new friends are made. Leisure hours are spent with a few friends doing
typical activities. Pay is considered as fair for the work done.
2 Work is difficult. Coworkers complain about the low pay and poor conditions.
On some weekends it is possible to spend time with a few friends, but other
weekends are boring.
1 (Worst) Work is extremely difficult, and working conditions are poor. Time off work
is generally boring because outside activities are limited or no friends are
available.
Let’s sum up the given information
Decision to make :
– Which job to take (In-town job or forest job)

Objectives (measures)
• Earning money (measured in $)

• Having fun
(measured using a constructed 5-point Likert scale)

Uncertain Events
• Amount of fun
• Amount of work
Summer Job Example-Influence Diagram
Summer Job Example- Decision Tree
The decision tree reflects Sam’s belief that
in-town job will give level 3 fun, but there
is considerable uncertainty about the level
of fun at the forest job. It also reflects the
uncertainty about the amount of work at the
in-town job.
Summer Job Example- One objective at a time
Analysis of the Salary Objective
Summer Job Example- One objective at a time
Analysis of the Fun Objective

The ratings in the original 5-point Likert scale


only indicate orders of the amount of fun without
carrying quantitative meanings. For example, the
increase in the amount of fun from level 2 to level
3 is not the same as that from level 3 to level 4.

The original ratings are rescaled to 0 -100 points


to show quantitative meanings:
5(best) – 100 points, 4(Good) – 90 points,
3(Moderate) – 60 points, 2(bad) – 25 points,
1(worst) – 0 point
Summer Job Example
Summer Job Example- Trade Off Analysis
– Steps
• First, multiple objectives must have Multiple objectives must have
1 comparable scales
comparable scales
x  xi
U i ( x)  
• Next, assign weights to these objectives (the xi  xi
sum of all the weights shouldbe equal to 1) xi :best value for attributei
– Subjective judgment xi :worst value for attributei
– Paying attention to the ranges of the attributes
(the variables to be measured in the objectives) Convert the salary scale to the same 0 to 100
is crucial; Attributes having wide ranges of scale used to measure fun
possible values are usually important (why?) Set $2730 (the highest salary) = 100, and
$2047.50 (the lowest salary) =0
• Then, calculate the weighted average of
consequences as an overall score

• Finally, compare the alternatives using the


overall score
Summer Job Example- Trade Off Analysis

Multiple objectives must


1 have comparable scales
x  xi
U i ( x)  
xi  xi
xi :best value for attributei
xi :worst value for attributei

Convert the salary scale to the same


0 to 100 scale used to measure fun
Set $2730 (the highest salary) =
100, and $2047.50 (the lowest
salary) =0
Summer Job Example- Trade Off Analysis
– Steps 2 Assign weights to these objectives
• First, multiple objectives must have
comparable scales

• Next, assign weights to these objectives (the The weights reflect personal judgment about the
sum of all the weights shouldbe equal to 1) relative importance of the two attributes.
– Subjective judgment
– Paying attention to the ranges of the attributes Let’s Assign weights to salary and fun (Ks and Kf)
(the variables to be measured in the objectives) Sam thinks increasing salary from the lowest to the
is crucial; Attributes having wide ranges of highest is 1.5 times more important than improving
possible values are usually important (why?) fun from the worst to best, hence Ks=1.5Kf ,
Because Ks+Kf=1 Ks=0.6, Kf=0.4
• Then, calculate the weighted average of
consequences as an overall score

• Finally, compare the alternatives using the


overall score
Summer Job Example- Trade Off Analysis
– Steps 3 Calculate the weighted average of
• First, multiple objectives must have consequences as an overall score
comparable scales
Sam decided to use the weights of 0.6 for salary
• Next, assign weights to these objectives (the and 0.4 for fun. That reflects his judgment that
sum of all the weights shouldbe equal to 1) the range of possible salaries is 1.5 times as
– Subjective judgment important as the range of possible summer-fun
– Paying attention to the ranges of the attributes ratings.
(the variables to be measured in the objectives)
is crucial; Attributes having wide ranges of With these weights, we can collapse the
possible values are usually important (why?) consequence matrix.

• Then, calculate the weighted average of For example, if Sam chooses the forest job and
consequences as an overall score the level of fun turns out to be Level 4 (score
90), the overall score is 0.60•(81) + 0.40•(90)
• Finally, compare the alternatives using the = 84.6. The other endpoint values in Figure
overall score 4.36 can be found in the same way.
Summer Job Example- Trade Off Analysis
Summer Job Example- Trade Off Analysis

4 Compare the alternatives using the overall score


Any
Questions?
In d u s t rial En gi n eeri n g| MARMARA UNIVERSIT Y

See you next lecture…

You might also like