-
APPLICATION OF THE ANALYTIC HIERARCHY PROCESS IN SUPPLIER
EVALUATION AND SELECTION
A project report submitted in partial fulfilment of the
Requirements for the award of the degree of
Bachelor of Information Technology
By:
Mohammed Khalid Alharthi
Salman Awed Alatwi Sultan EtanAlbalawi
Yasser Mohammed Alabalawi
Supervised By:
Dr. Osman Ahmed Abdalla
Department of Information Technology
Faculty of Computers and Information Technology
University of Tabuk
December 2014
-
ii
DECLARATION
I hereby declare that this project report is based on my
original work except for citations
and quotations which have been duly acknowledged. I also declare
that it has not been
previously and concurrently submitted for any other degree or
award at University of Tabuk or
other institutions.
Name ID No. Signature
MOHSMMED KHALID ALHARTHI 321000020
SALMAN AWED ALATWI 321001865
SULTAN ETANALBALAWI 321002504
YASSER MOHAMMEDALBALAWI 321001533
Date : _________________________
APPROVAL FOR SUBMISSION
I certify that this project report entitled "SUPPLIER SELECTION"
was prepared by
Mohammed Khalid Alharthi , Salman Awed Alatwi, Sultan
EtanAlbalabwi, Yasser
Mohammed Albalawihas met the required standard for submission in
partial fulfilment of the
requirements for the award of Bachelor of information technology
at University of Tabuk.
-
iii
Approved by,
Signature : _________________________
Supervisor : Dr. Osman Ahmed Abdalla
Date : _________________________
The copyright of this report belongs to the author and is
protected under the intellectual
property right laws and conventions. It can only be
considered/used for purposes like extension for
further enhancement, product development, adoption for
commercial/organizational usage, etc.,
with the permission of the University of Tabuk.
2014, University of Tabuk. All right reserved
-
iv
ACKNOWLEDGEMENTS
We would like to thank everyone who had contributed to the
successful completion of this
project. We would like to express my gratitude to my research
supervisor, Dr. Osman Ahmed for
his invaluable advice, guidance and his enormous patience
throughout the development of the
research.
In addition, we would also like to express our gratitude to my
loving parent and friends
who had helped and given our encouragement......
-
v
APPLICATION OF THE ANALYTIC HIERARCHY PROCESS IN
SUPPLIER EVALUATION AND SELECTION
ABSTRACT
The aim of this project is to employ the Analytic Hierarchy
Process (AHP) method in
order to select the best supplier of personal computers PC
purchasing in university of
Tabuk. AHP is powerful and most popular mathematical technique
for multi-criteria
decision making. One of the major problems and challenges that
facing the modern
organization and companies is the process of selecting the best
supplier of products, raw
materials, materials, machines, equipment, and services
selection . This process may take
long time and select the wrong supplier.
The propose methodology are:
Determine the data of suppliers with adequate criteria,
sub-criteria and alternatives
structure of the hierarchical model , prioritize the order of
criteria or sub-criteria , measure
the suppliers performance and Identify supplier's priority and
selection.
Propose AHP method contributes in helping decision maker to
select the best supplier with
high level of confidence, less time and effort consuming.
-
vi
-
vii
TABLE OF CONTENTS
CONTENTS Page No.
DECLARATION II
ACKNOWLEDGEMENTS IV
ABSTRACT V
TABLE OF CONTENTS VII
LIST OF TABLES VIII
LIST OF FIGURES IX
LIST OF ABBREVIATIONS X
Chapter 1 1
1.1 Background : 1
1.2 Statement of the problem: 2
1.3 Objectives: 2
1.4 The AHP method : 2
1.5 Layout : 3
Chapter 2 4
Background and literature review 4
2.1 decision making 4
2.2 supplier selection 4
2.3 supplier selection process : 5
2.4 supplier selection methods : 5
2.5 the analytic hierarchy process : 7
2.6 how AHP works 8
2.7 AHP details 9
Chapter 3 10
Methodology 10
3.1 Planning 11
3.2 Analysis 12
3.3 Design 13
3.3.1 Model formulation 13
3.4 Implementation 18
3..5 Requirements analysis 20
3.5.1 Use case 20
4.Use case specifications 21
5. Database table 25
Chapter 4 26
Design 26
4.1. User log in 26
4.2. Compared to criteria 27
4.3. compared to a price of preference screen 27
-
viii
4.4. Compared to a memory of preference screen 28
4.5. Compared to storage of preference screen 28
4.6.Compared to delivery of preference screen 29
4.7.Result of selection screen 29
REFERENCES 30-31
LIST OF TABLES
TABLE Page No
Table of Contents VII
List of Tables VIII
List of Figures IX
LIST OF ABBREVIATIONS X
Table3. 1 project phases 11
Table: 3. 2 The test data 11
Table: 3.3 measurement scale3 AHP measurement scale 13
Table:3. 4 AHP example: original matrix 14
Table3. 5 AHP example: normalized matrix 14
Table:3. 6 AHP example: processer matrix 15
Table :3.7 AHP example: normalized processer matrix 15
Table:3. 8 AHP example: memory matrix 15
Table:3. 9 AHP example: normalized memory matrix 16
Table:3. 10 AHP example: int-storage matrix 16
Table :3.11 AHP example: normalized int-storage matrix 16
Table :3.12 AHP example: price matrix 17
Table:3. 13 AHP example: normalized price matrix 17
Table :3.14 AHP example: delivery matrix 17
Table:3. 15 AHP example: normalized delivery matrix 18
Table:3. 16 AHP example: summary of results 18
Table: 4.1 Log in 21
Table: 4.2 Compared to criteria 22
Table: 4.3 Compared every criteria of preference 23
-
ix
Table: 4.4 View result 24
table:5.1 User table 25
Table:5.2 User table 25
LIST OF FIGURES
Figure Page No.
Figure 2.1 The general AHP hierarchy 7
Figure 3.1 SDLC waterfall methodology 10
Figure 3.2 Hierarchy of the AHP example 12
Figure 3.3 login use case Main Interface 20
Figure 4.1 main interface 26
Figure 4.2 Interface compared to criteria 27
Figure 4.3 Interface compared to a price of preference 27
Figure 4.4 Interface compared to a memory of preference 28
Figure 4.5 Interface compared to storage of preference 28
Figure 4.6 Interface compared to delivery of preference 29
Figure 4.7 Interface as a result of selection 29
-
x
LIST OF ABBREVIATIONS
DEA Data Envelopment Analysis
AHP Analytical Hierarchical Process
ANP Analytic Network Process
TCO Total Cost of Ownership
TOPSIS
Solution
Technique for the Order Performance by Similarity to Ideal
MAUT Multiple Attribute Utility Theory
CBR Case-Based-Reasoning
ANN Artificial Neural Network
RAD Rapid Application Development Process
OPM Option Performance Matrix
-
1
CHAPTER 1
INTRODUCTION
1.1 Background :
Choosing the right supplier involves much more than scanning a
series of price lists.
This will depend on a wide range of factors such as speed
process manager hardest, price and
delaying further to specify the importance of these different
factors will be based on your
business' priorities and strategy
Decision making is a key activity and the most important issue
in business. Commonly, the
managers locking for reliable and correct forecast for their
decisions. To achieve this goal they
should consider scientific criteria. The main problem that
facing a decision maker is the
selecting of most appropriate alternative according to at least
one goal or criteria from the
alternatives cluster [1].
Nowadays, the interesting of decision makers about supplier
selection process has
been rapidly growing because reliable or correct suppliers
support in reduction of inventory
costs and the improvement of product quality [2].
For modern organizations and companies the selection of a
supplier is become the most
important step in creating a successful alliance. The selection
of a suitable supplier is a
significant factor affecting eventual buyersupplier
relationship. If the selection process is
completed correctly, a higher quality, longer lasting
relationship is more achievable [3].
Supplier selection is the process of finding the appropriate
suppliers being able to provide the
purchaser with the right quality products/services at the right
price, in the right quantities and
at the right time [4]. Supplier selection includes activities to
solve the conflicts between the
buyer and suppliers on the details of products/services.
Most related literatures on supplier selection have been focused
on the decision making
approaches. [4] presented a survey of decision methods reported
in the literature for
supporting supplier selection process. [5] analysed the decision
making methods that have
been utilized for supplier selection based on journal articles
from 2000 to 2008. Then,
frequently used of AHP method to solve the multi-criteria
decision-making problem of
supplier selection is proposed by [6, 7, 8, and 9].
This project focuses on Analytical Hierarchical Process (AHP)
which is a decision
making method developed for prioritizing alternatives when
multiple criteria must be
-
2
considered and allows the decision maker to structure complex
problems in the form of a
hierarchy, or a set of integrated levels. This method
incorporates qualitative and quantitative
criteria. The hierarchy usually consists of three different
levels, which include goals, criteria,
and alternatives. Because AHP utilizes a ratio scale for human
judgments, the alternatives
weights reflect the relative importance of the criteria in
achieving the goal of the hierarchy
The AHP Advantages can be summarized are as follows:
Unity can construct single, easily understood, flexible models
for a broad range of
unstructured problems.
Hierarchic Structuring utilizes the natural tendency of people
to sort elements of a system
into different levels and to group like elements.
Consistency - does not require judgments to be consistent.
Synthesis determines the relative importance of the criteria in
meeting a goal.
Process Repetition - enables the refinement of the definition of
a problem; improves judgment
and understanding through repetition.
1.2 Statement of The Problem:
Supplier selection decisions are usually dependent upon various
criteria; however
decision maker usually focuses only on the price of materials or
services only. Supplier
selection process may contain huge number of suppliers which
takes time and need a lot of
effort to make the right decision. Any biased and poor decision
might be made would
negatively influence the whole business in the organization.
1.3 Objectives:
The main objective of this project is to develop a supplier
selection model based on
Analytical Hierarchy Process model (AHP). The proposed model
should:
Support decision making by provide a judgment of supplier
selection with a highly
confidence.
Reduce consuming of time, effort, and increase the quality in
the supplier selection process.
1.4 The AHP Method :
The AHP Method Steps Can be Summarized as:
Step 1: Model the problem as a hierarchy containing the decision
goal, the alternatives for
reaching it, and the criteria for evaluating the
alternatives.
-
3
Step 2: Establish priorities among the elements of the hierarchy
by making a series of
judgments based on pairwise comparisons of the elements. For
example, when comparing
potential purchases of commercial real estate, the investors
might say they prefer location over
price and price over timing.
Step 3: Synthesize these judgments to yield a set of overall
priorities for the hierarchy. This
would combine the investors' judgments about location, price and
timing for properties A, B,
C, and D into overall priorities for each property.
Step 4: Check the consistency of the judgments.
Step 5: The final decision based on the results of this
process
1.5 Layout :
This project is documented in 3 chapters. Chapter one introduces
the research problem
and objectives. Chapter two will give an introduction to
decision-making, and provide a
discussion about the supplier selection, the model Analytical
Hierarchy Process (AHP) that we
have applied, In lastly the chapter three, will explain the
methodology.
-
4
CHAPTER 2
BACKGROUND AND LITERATURE REVIEW
One of the most important processes performed in organizations
today is the
evaluation, selection, and continuous improvement of suppliers.
This review first will include
the general framework used in the supplier selection process and
the different types of
suppliers. Next, some of the existing methods of supplier
selection are discussed followed by a
supplier evaluation system, several software packages useful for
these processes are presented.
2.1 Decision Making
The decision-making process a major activity practiced daily by
managers regardless
of their administrative levels, but the degree of importance of
the decision varies depending on
the levels. There are two types of decision-making first
programmed a repetitive nature and
decisions is programmed with a new character and undefined.
There are two entrances to the
two decision-making individual decisions entrance and the
entrance to regulatory decisions, as
well as quantitative approaches to decision-making and according
to specific criteria, and that
all these approaches is a guide for decision-makers to take
decisions properly and correctly.
2.2 Supplier Selection
The supplier selection function in modern enterprises and
organizations is more
complicated process in which including the process of selecting
the following criteria: quality,
delivery performance, production facilities, warranty claims,
price and technical capabilities
need to be applied [10].
Some authors have identified several criteria for supplier
selection, such as the net
price, quality, delivery, historical supplier performance,
capacity, communication systems,
service, and geographic location, among others [11, 12]. These
criteria are a key issue in the
supplier assessment process since it measures the performance of
the suppliers.
In general, this research intends to provide empirical evidence
of the criteria and the
procedures for the supplier selection process used in different
corporate environments. Finally,
identify the suitability of the Analytical Hierarchical Process
(AHP) to assist in decision
making to resolve the supplier selection problem.
The Analytic Hierarchy Process is a systematic method widely
used for decision
problems with many criteria and alternatives first developed by
[13]. It is a tool used for
-
5
solving complex decision problems that may have correlations
among decision criteria based
on three principles: decomposition, comparative judgments and
synthesis of priorities.
Traditionally organizations have been divided in operative
functions such as
marketing, planning, production, purchasing, finance, etc.
Supply chain is a strategy that
integrates these functions creating a general plan for the
organization, which satisfies the
service policy, maintaining the lowest possible cost level due
the incredible competition
environment that they are exposed to. A supply chain is a
network of departments, which is
involved in the manufacturing of a product from the procurement
of raw materials to the
distribution of the final products to the customer.
2.3 Supplier Selection Process :
Experts agree that no best way exists to evaluate and select
suppliers, and thus
organizations use a variety of approaches. The overall objective
of the supplier evaluation
process is to reduce risk and maximize overall value to the
purchaser. An organization must
select suppliers it can do business with over an extended period
of time.
Supplier evaluations often follow a rigorous, structured
approach through the use of a survey.
An effective supplier survey should have certain characteristics
such as comprehensiveness,
objectiveness, reliability, flexibility and finally, has to be
mathematically straightforward. To
ensure that a supplier survey has these characteristics is
recommended a step-by-step process
when creating this tool.
2.4 Supplier Selection Methods :
There are several supplier selection methods and multi-criteria
decision making, therefore,
It is difficult to find the best method evaluate and select the
best supplier, thus, the most
important issue in the process of supplier selection is to
develop a suitable method to select the
right supplier [14]. Many authors proposed and used have been
developed different methods
for supplier evaluation and selection. These are; linear
weighted models, total cost models,
mathematical programming models, statistical models and
artificial intelligent (AI) based
techniques.
In linear weighted models, each criterion is being weighted and
suppliers performance
is multiplied by this weight for each criteria. The sum of these
multiplications represents the
total performance of supplier. Although it is a very simple
method, it depends heavily on
human decision and also weights the attributes equally, which
rarely happens in practice. It is
-
6
divided as categorical method, weighted point model (linear
weighted model) and analytical
hierarchy process (AHP) model. In categorical method, the
criteria are weighted equally and
the decisions by made with this method are subjective. In
weighted point model, because of
the total criteria performance, the criterion with low
performance is not taken into account. In
AHP model, human decision forms the main structure of comparison
matrices.
Total cost models are complex methods which depend to cost. They
consider not only
the products rate but also, indirect item cost. It is divided as
cost ratio method and ownership
total cost model. The cost ratio method is not widely used in
companies because it requires a
comprehensive cost accounting system which is only to be found
in large scaled companies
and has a complex structure. In ownership total cost model, the
potential risk is available
during the supplier selection process, the subjectivity cannot
be removed.
Mathematical models are used to represent the complex structure
of supplier selection
and have been widely used for modeling selection and allocation
problems. On the other hand,
Mathematical Programming (MP) models cause a significant problem
in considering
qualitative factors. The drawback of MP is that it requires
arbitrary aspiration levels and
cannot accommodate subjective attributes. Supplier selection is
a Multiple-Attribute Decision-
Making (MADM) problem. The decisionmakers (DMs) always express
their preferences on
alternatives or on the attributes of suppliers, which can be
used to help rank the suppliers or
select the most desirable one. The preference information on
alternatives of supplier and on
attributes belongs to the DMs subjective judgments. In
conventional MADM methods, the
ratings and weights of the attributes are known precisely.
Generally, DMs judgments are
often uncertain and cannot be estimated by an exact numerical
value. Thus, the problem of
selecting suppliers has many uncertainties and becomes more
difficult. In conventional
MADM methods, the ratings and the weights of attributes must be
known precisely. However,
in many situations DMs judgments are often uncertain and cannot
be estimated by an exact
numerical value [15]. The most used are: linear programming,
integer programming, mixed
integer programming, multi criteria programming and goal
programming.
For using the statistical approaches, it is essential to reach
implicit and accurate
knowledge about suppliers. Obtained knowledge about previous
performances of suppliers are
significant for the usage of these models. The common models are
classification analysis and
fundamental components analysis.
-
7
Also, the methods such as data envelopment analysis, neural
networks, fuzzy set
theory, and analytic network process and quality function
deployment are used for supplier
selection.
2.5 The Analytic Hierarchy Process :
The analytic hierarchy process (AHP) is a mathematical
multi-criteria decision-making
method (MCDM) for dealing with multi-attribute and unstructured
problems. It was proposed
by [13], the author of the celebrated AHP method, has recently
been gaining widely used and
popular. AHP is conceptually easy to use; however, it breaks
down a complex problem into
several levels in order to generate a hierarchical structure
with unidirectional hierarchical
relationships between levels. This structured hierarchy aim to
determine the impact of the
lower level on an upper level, and this is attained by paired
comparisons provided by the
decision-maker. The upper level represents the main goal of the
decision problem, whereas the
lower levels of the hierarchy represent the tangible and/or
criteria, sub-criteria and alternatives
that contribute to the goal Figure1
.
Figure 2.1 The general AHP hierarchy
(http://en.citizendium.org/wiki/Analytic_Hierarchy_Process)
There are many outstanding works that have been published based
on AHP: these
works applied AHP in different fields, such as selecting a best
candidate as in our case,
evaluation, resource allocations, planning, , resolving
conflicts, benefits cost analysis,
optimization, forecasting, etc., as well as priority and
ranking.
The AHP divides the decision problem into three main steps:
Problem structuring.
-
8
Assessment of local priorities.
Calculation of global priorities.
First, the problem is structured hierarchically, i.e. the
decision maker constructs the
hierarchies of factors for solving the decision problem. The
overall goal is represented by the
upper level of the hierarchy; one or more intermediate levels
correspond to the hierarchy of
the decision criteria, while the lower level consists of all
considered alternatives.
The term local priority is used both for the weights of the
criteria and sub-criteria and
for the rating scores of the alternatives. The assessment of
local priorities is performed after
the decision maker provides his preferences by pair wise
comparisons among factors in each
level of the hierarchy. Saaty introduced in [13] a nine-point
numerical scale to represent the
relative degree of importance for two factors, where the value
of 1 stands for equally
preferred, the value of 2 stands for equally to moderately
preferred and so forth up to the
value of 9 that stands for extremely preferred. After the
comparisons have been per-formed,
a pair-wise comparison matrix A is constructed, in which element
Aijof the matrix is the
relative importance of the ith factor with respect to the jth
factor at the same level of the
hierarchy. Obviously, the relation Aij=1/Ajialways holds and
therefore A is a positive
reciprocal matrix:
A =
The values of weights Wiof the criteria may be obtained from the
comparison matrix
by applying a prioritization technique such as the Eigenvector
analysis, the Logarithmic Least
Squares method, the Goal Programming method or the Fuzzy
Programming method [16-19].
The values of the rating score Riof the alternatives are also
obtained from the comparison
matrix for each criterion corresponding to the alternatives in
the lower level of the hierarchy.
2.6 How AHP Works
The AHP offers a methodology to rank alternative courses of
action based on the
decision makers judgments concerning the importance of the
criteria and the extent to which
-
9
they are met by each alternative. For this reason, AHP is
ideally suited for the supplier
selection problem.
The problem hierarchy lends itself to an analysis based on the
impact of a given level
on the next higher level. The process begins by determining the
relative importance of the
criteria in meeting the goals. Next, the focus shifts to
measuring the extent to which the
alternatives achieve each of the criteria. Finally, the results
of the two analyses are synthesized
to compute the relative importance of the alternative in meeting
the goal.
Managerial judgments are used to drive the AHP approach. These
judgments are
expressed in terms of pair wise comparisons of items on a given
level of the hierarchy with
respect to their impact on the next higher level. Pair wise
comparisons express the relative
importance of one item versus another in meeting a goal or a
criterion. Each of the pair wise
comparisons represents an estimate of the ratio of the weights
of the two criteria being
compared. Because AHP utilizes a ratio scale for human
judgments, the alternatives weights
reflect the relative importance of the criteria in achieving the
goal of the hierarchy.
2.7 AHP Details
The use of the AHP approach offers a number of benefits. One
important advantage is
its simplicity. The AHP can also accommodate uncertain and
subjective information, and
allows the application of experience, insight, and intuition in
a logical manner.
The AHP approach, as applied to the supplier selection problem,
consists of the
following five steps [20]:
1. Specify the set of criteria for evaluating the suppliers
proposals.
2. Obtain the pair wise comparisons of the relative importance
of the criteria in
achieving the goal, and compute the priorities or weights of the
criteria based on
this information.
3. Obtain measures that describe the extent to which each
supplier achieves the
criteria.
4. Using the information in step 3, obtain the pair wise
comparisons of the relative
importance of the suppliers with respect to the criteria, and
compute the
corresponding priorities.
5. Using the results of steps 2 and 4, compute the priorities of
each supplier in
achieving the goal of the hierarchy.
-
10
CHAPTER 3
METHODOLOGY
This project is based on the Waterfall model of Systems
Development Life Cycle
(SDLC) methodology whereby construction of the system flows from
top to bottom. It is a
structured sequential design process. The phases in the
development cycle consist of
feasibility study, systems analysis and requirements, system
design, implementation and
testing phases. Deliverables include system codes and this
system documentation.
The Waterfall model of Systems Development Life Cycle (SDLC)
methodology is
mainly based on in this project as shown in Figure2.
Figure 3.1 SDLC waterfall methodology
(http://businessobjectsforum.blogspot.com/2008/09/data-modeling-concepts-
chapter-1.html)
-
11
Table 1 illustrates the proposed project phases and the
description of each phase.
Phase Description
Project planning, feasibility
study
A high-level view of the intended project is
established.
Systems analysis, requirements
Definition
End-user requirements are identified
and analyzed.
System design Desired features and operations are described
in
detail, including screen layouts, business rules,
process diagrams and other documentations.
Implementation Real code of the system is written.
Testing System is presented and errors and bugs are checked.
Table3. 1 Project Phases
3.1 Planning
The planning phase means project initiation. The planning phase
will take part in the
first semester. The main activities that will be executed during
the planning phase include
AHP application model.
And we'll select the required standards according to the
requirements of the system and
the application of the model to the data. We apply the selection
system supplier to make sure
you apply it correctly and give satisfactory results.
The first important issue in this project is to collect related
data. First a conceptual
model including data on the University of Tabuk for 3 supplier
attempt 5 criteria that is
typically used for determine the best supplier such as :(
Processor, Memory, Intstorage, Price
and delivery) so the decision depend on this criteria. Table 2
shows the selected criteria for the
3 supplier.
S1 S2 S3
Processor 1.86 3.66 1.86
Memory 1024 2000 1024
Int-storage 146.8 440.4 146
Price 20352 48200 25320
Delivery 4 3 6
Table: 3. 2 The test data
The main objective of this phase is to gathering the data and to
gain full understanding
regarding all components. The planning phase is vital as it is
the foundation for the project and
the planning phase will determine the course of direction for
the project.
-
12
3.2 Analysis
AHP method is a good choice for handling our gathered data. AHP
is the one of the
most systematic analytical techniques of MCDM within the
framework of operational research
techniques that facilitates a rigorous definition of priorities
and preferences of DMs. It is
widely used as an analytical tool in various fields of studies.
Broadly the technique considers
the following steps during modeling of any system under
consideration:
(a) Defining a site-specific hierarchic structure;
(b) Calculating weights.
(c) Compared the ratios.
Figure 3.2 Hierarchy of the AHP example
First in the analysis phase and should be available to us are
three elements to the
system we design, a methodology, and suppliers, and services
suppliers.
Methodology that has been identified is a rapid application
development, and here we
chose model (AHP) as hosts previously and our goal is to help in
the consumption of time.
Suppliers: suppliers must be available to enter the competition
for the tender under the
terms of the tender, and in our system we have three suppliers
are the ones who lose access to
the tender.
Services Suppliers: represented in the services they provide, as
requested by the
company's existing tender In our experience the company needs
computer hardware and
-
13
focused on five criteria and provide enough information about to
enter into the selection
process which (Processor, Memory, Int-storage, Price, Delivery)
as hosts in the Table 2 and
we'll build the system according to these basics.
3.3 Design
The design phase will focus on the design of tables and
equations, through which we
will apply the AHP model.
3.3.1 Model formulation
The AHP approach, which applied to the supplier selection
problem, consists of the
following steps:
i. Specify the set of criteria for evaluating the suppliers
proposals.
ii. Obtain the pair wise comparisons of the relative importance
of the criteria in
achieving the goal, and compute the priorities or weights of the
criteria based on this
information.
iii. Obtain measures that describe the extent to which each
supplier achieves the criteria.
iv. Using the information in step 3, obtain the pair wise
comparisons of the relative
importance of the suppliers with respect to the criteria, and
compute the
corresponding priorities.
v. Using the results of steps 2 and 4, compute the priorities of
each supplier in
achieving the goal of the hierarchy.
Assume there are 5 criteria that are being used to evaluate 3
suppliers. This will be
applied by steps for the selected scale in the model of AHP:
Table: 3.3 MEASUREMENT SCALE3 AHP Measurement scale
Verbal Judgment of Preference Numerical Rating
Extremely Prefered 9
Very Strongly Prefered 7
Strongly Prefered 5
Moderately Prefered 3
Equal y Preferred 1
-
14
The buyer must now develop a set of pair wise comparisons to
define the relative
importance of the criteria to complete the following matrix
(Table 4). Table 4 AHP Example:
Original Matrix
Processor Memory Int-storage Price Delivery
Processor 1 3 7 9 9
Memory 0.33 1 5 9 9
Int-storage 0.14 0.2 1 5 7
Price 0.11 0.11 0.2 1 3
Delivery 0.11 0.11 0.14 0.33 1
Total 1.69 4.42 13.34 24.33 29
Table:3. 4 AHP Example: Original Matrix
The data in the matrix can be used to generate a good estimate
of the criteria weights.
The weights provide a measure of the relative importance of each
criterion.
This process is summarized in the following three steps, and
shown in the Table 5:
1. Sum the elements in each column.
2. Divide each value by its column sum.
3. Compute row averages
Processor Memory Int-storage Price Delivery Weights
Processor 0.591716 0.678733 0.52473763 0.369914 0.310345
0.495089
Memory 0.195266 0.226244 0.37481259 0.369914 0.310345
0.295316
Int-
storage
0.08284 0.045249 0.07496252 0.205508 0.241379 0.129988
Price 0.065089 0.024887 0.0149925 0.041102 0.103448 0.049904
Delivery 0.065089 0.024887 0.01049475 0.013564 0.034483
0.029703
Total 1 1 1 1 1 1
Table3. 5 AHP Example: Normalized Matrix
-
15
Next, the three suppliers must be compared pair wise for each
criterion. This process is
virtually identical to the procedure that was used to develop
the criteria comparison
matrix. The only difference is that there is a supplier
comparison matrix for each
criterion. Therefore, the decision maker compares each pair of
suppliers with respect to
the quality criterion, as shown in Table 6:
Supplier1 Supplier2 Supplier3
Supplier1 1 0.33 1
Supplier2 3 1 3
Supplier3 1 0.33 1
Total 5 1.66 5
Table:3. 6 AHP Example: processer matrix
Supplier1 Supplier2 Supplier3 Weights
Supplier1 0.2 0.19879518 0.2 0.199598
Supplier2 0.6 0.60240964 0.6 0.600803
Supplier3 0.2 0.19879518 0.2 0.199598
Total 1 1 1 1
Table :3.7 AHP Example: Normalized processer matrix
Furthermore, the memory criterion is compared with each pair of
suppliers (Table 8 and
Table 9):
Supplier1 Supplier2 Supplier3
Supplier1 1 0.2 1
Supplier2 5 1 5
Supplier3 1 0.2 1
Total 7 1.4 7
Table:3. 8 AHP Example: memory matrix
-
16
Supplier1 Supplier2 Supplier3 Weights
Supplier1 0.142857 0.142857 0.142857 0.142857
Supplier2 0.714286 0.714286 0.714286 0.714286
Supplier3 0.142857 0.142857 0.142857 0.142857
Total 1 1 1 1
Table:3. 9 AHP Example: Normalized memory matrix
Also, the service criterion is compared with each Int-storage of
suppliers (Table 10 and
Table 11):
Supplier1 Supplier2 Supplier3
Supplier1 1 0.2 3
Supplier2 5 1 7
Supplier3 0.34 0.14 1
Total 6.34 1.34 11
Table:3. 10 AHP Example: Int-storage matrix
Supplier1 Supplier2 Supplier3 Weights
Supplier1 0.157729 0.1492537 0.272727 0.193237
Supplier2 0.788644 0.7462687 0.636364 0.723759
Supplier3 0.053628 0.1044776 0.090909 0.083005
Total 1 1 1 1
Table :3.11 AHP Example: Normalized Int-storage matrix
-
17
Consequently, the Price criterion is compared with each pair of
suppliers (Table 12
and Table 13):
Supplier1 Supplier2 Supplier3
Supplier1 1 9 5
Supplier2 0.11 1 0.11
Supplier3 0.2 9 1
Total 1.31 19 6.11
Table :3.12 AHP Example: Price matrix
Supplier1 Supplier2 Supplier3 Weights
Supplier1 0.763359 0.473684 0.818331 0.685125
Supplier2 0.083969 0.052632 0.018003 0.051535
Supplier3 0.152672 0.473684 0.163666 0.263341
Total 1 1 1 1
Table:3. 13 AHP Example: Normalized Price matrix
Consequently, the delivery criterion is compared with each pair
of suppliers (Table 14
and Table 15):
Supplier1 Supplier2 Supplier3
Supplier1 1 0.34 3
Supplier2 3 1 5
Supplier3 0.34 0.2 1
Total 4.34 1.54 9
Table :3.14 AHP Example: Delivery matrix
-
18
Supplier1 Supplier2 Supplier3 Weights
Supplier1 0.230415 0.220779 0.333333 0.261509
Supplier2 0.691244 0.649351 0.555556 0.63205
Supplier3 0.078341 0.12987 0.111111 0.106441
Total 1 1 1 1
Table:3. 15 AHP Example: Normalized delivery matrix
The final step of the AHP analysis is summarized in Table
16.
Processor Memory Intstorage Price Delivery score
Supplier1 0.098819 0.042188 0.0251184 0.03419 0.007768
0.208083
Supplier2 0.297451 0.21094 0.0940797 0.002572 0.018774
0.623817
Supplier3 0.098819 0.042188 0.0107896 0.013142 0.003162
0.164938
Table:3. 16 AHP Example: Summary of Results
According to the previous results, the higher weight belongs to
supplier 2, and is
judged to be the best overall.
Among the decision support methods, application of the AHP
method to the supplier
selection problem is not new in the artisan be conducted with
multi objective such as
neural network or expert system so we can related with other
techniques . We apply the
AHP model in vb.net program and we link it with Excel and we'll
show you in the next
chapter some forms after completion of the system.
3.4 Implementation
In the implementation phase, we will clarify the equations that
have been applied in the
previous tables.
a) Preparation A norm natural matrix by a process of division of
each element in
the matrix A in column i to the sum of all elements in the same
column as
follows:
-
19
Rij= aij/ . (1)
I = 1, 2..N
Rij: Natural element of the matrix Anorm
We apply this equation to the previous tables of matrixes
b) Calculate weights matrix "W", if you represent these weights
vectors
preference among alternatives according to the criteria, for
example, calculates
the weight of the row (i), which represents a variant of the
matrix "W" grade
average of the elements of the matrix A also comes:
Wi= (1/N) .. (2)
Wi : Represents the preference vector Or What called Priority
vector.
I = 1, 2..N
We apply this equation to the previous tables of Normalized.
We will show in the next chapter the results after the design of
the program and associate
it with these equations.
-
20
3.5 Requirements Analysis
3.5.1 Use case
Figure 3.3 login use case
-
21
4. Use Case Specifications
4.1 Log in use case
Use Case ID: 1
Use Case Name: Log in
Actors: User
Description: A user has to enter to the system before
work in the system.
Post conditions: 1. user enter to main menu in the system
Normal Flow: 1. user open the system icon
2. System prompt form user his username
and password and confirms it.
3. System verify the data
4. main screen show
5. use case end
3.if user is valid the system will show
main menu.
Alternative Flows: 1.
Exceptions: E.1 Incorrect Username/Password 1.
System prompts user to re-type
username/password.
2.User re-enters username/password.
Includes: None
Table: 4.1 Log in
-
22
4.2 Compared to criteria use case
Use Case ID: 2
Use Case Name: Compared to criteria
Actors: User
Description: A user select Compared to criteria as
first step in the select supplier process
Post conditions: 1. user enter every criteria value
Normal Flow: 1. User choose to Compared to criteria
2. System display Compared to criteria
screen
3.user select every criteria value
4.user save data
5.use case end
Alternative Flows: 1.
Exceptions: E.1 empty data 1. System prompts user to
re-enter criteria value
Includes: None
Table: 4.2 Compared to criteria
-
23
4.3 Compared every criteria of preference
Use Case ID: 3
Use Case Name: Compared every criteria of preference
Actors: User
Description: A user select Compared every criteria of
preferences second step in the select
supplier process
Post conditions: 1. user enter suppliers criteria value
Normal Flow: 1. User choose to Compared every
criteria of preference
2. System display Compared every
criteria of preference screen
3.user select every supplier value for
criteria
4.user save data
5.use case end
Alternative Flows: 1.
Exceptions: E.1 empty data 1. System prompts user to
re-entercriteria value
Includes: None
Table: 4.3 Compared every criteria of preference
-
24
4.4 View result use case
Use Case ID: 4
Use Case Name: view result
Actors: User
Description: A user select view result of the best
suppliers
Post conditions: 1. system display every supplier and his
rank
Normal Flow: 1. User choose to view result
2. System display suppliers list and their
rank
3.use case end
Alternative Flows: 1.
Exceptions:
Includes: None
Table: 4.4 View result
-
25
5. Database table
5.1 Users table
Field name Data type Key Null value Default value
ID Int primary key not null
user_nam nvarchar(50) not null
user_passward nvarchar(50) not null
Table:5.1 User Table
Field name Data type Key Null value Default value
SUPPLIER_id Int primary key not null
SUPPLIER_name nvarchar(40) not null
SUPPLIER_address nvarchar(50) null
SUPPLIER_email nvarchar(40) null
SUPPLIER_phone nvarchar(15) null
SUPPLIER_mobile nvarchar(15) null
SUPPLIER_fax nvarchar(15) null
SUPPLIER_notes nvarchar(100) null
Table:5.2 User Table
-
26
Chapter 4
DESIGN
4.1 Design
We will in this section the system design will be
illustrated
4.1. User log in
Figure 4.1 main interface
The use log in screen allow users to enter the system after
verify their user name and password
-
27
4.2. Compared to criteria
Figure 4.2 Interface compared to criteria
Compared criteria screen user depend on the decision-making
process.
4.3. compared to a price of preference screen
Figure 4.3 Interface compared to a price of preference
-
28
4.4. Compared to a memory of preference screen
Figure 4.4 Interface compared to a memory of preference
4.5. Compared to storage of preference screen
Figure 4.5 Interface compared to storage of preference
-
29
4.6.Compared to delivery of preference screen
Figure 4.6 Interface compared to delivery of preference
4.7.Result of selection screen
Figure 4.7 Interface as a result of selection
Finally, as shown when the button is pressed out to get out of
the system note that the last
result to be reserved in the system when you log on to the
system again put pressure on the
button get result And introduce us to the last saved result.
-
30
REFERENCES
[1] Erol,V.,Balgil,
H.,letmelerdeynetimbiliimsistemiyazlmseimiiinanalitikhiyerariprosesiveyapa
ysiniralarmodeli Mhendislikve Fen BilimleriDergisi, Sigma,
2005.
[2] Chamodrakas, I., Batis, D., Martakos, D., Supplier selection
in electronic
marketplaces using satisficing and fuzzy AHP, Expert Systems
with Applications,
vol.37 ,2010, pp. 490498.
[3] Lee, A.H.I., A fuzzy supplier selection model with the
consideration of
benefits, opportunities, costs and risks, Expert Systems with
Applications vol. 36
,2009, pp. 28792893.
[4] L. De Boer, E. Labro, P. Morlacchi, A review of methods
supporting supplier
selection,European Journal of Purchasing & Supply
Management, 7 (2) (2001), pp. 75
89.
[5] W. Ho, X. Xu, P.K. Dey, Multi-criteria decision making
approaches for
supplier evaluation and selection: A literature review, European
Journal of Operational
Research, 202 (1) (2010), pp. 1624.
[6] F.T.S. Chan, H.K. Chan, R.W.L. Ip, H.C.W. Lau, A decision
support system
for supplier selection in the airline industry, Proceedings of
the Institution of
Mechanical Engineers, Part B: Journal of Engineering
Manufacture, 221 (4) (2007), pp.
741758.
[7] A. Ishizaka, C. Pearman, P. Nemery, AHP sort: An AHP-based
method for
sorting problems, International Journal of Production Research,
50 (17) (2012), pp.
47674784.
[8] F. Mafakheri, M. Breton, A. Ghoniem, Supplier
selection-order allocation: A
two-stage multiple criteria dynamic programming approach,
International Journal of
Production Economics, 132 (1) (2011), pp. 5257.
[9] S.M. Ordoobadi, Application of AHP and Taguchi loss
functions in supply
chain, Industrial Management and Data Systems, 110 (8) (2010),
pp. 12511269. [10]
G.W. Dickson, An analysis of vendor selection systems and
decisions, Journal of
purchasing, 21 (1966), pp. 517.
[11] G. Dickson, An analysis of vendor election systems and
decisions, Journal of
Purchasing, 2 (1) (1966), pp. 517.
-
31
[12] Dempsey, W.. (1978). Vendor selection and the buying
process. Industrial
Marketing Management, 7, 257-267.
[13] Saaty T L (1980) The Analytic Hierarchy Process, McGraw
Hill International.
[13] Weber, C., Current, J. & Benton, W.. (1991). Vendor
selection criteria and
methods. European Journal of Operational Research, 50, 2-13.
[14] C. Chen, C. Lin, S. Huang, A fuzzy approach for supplier
evaluation and
selection in supply chain management, International Journal of
Production Economics,
102 (2006), pp. 289301.
[15] Li DF (2007). Compromise Ratio Method for Fuzzy
Multi-attribute Group
Decision Making. [doi: DOI: 10.1016/j.asoc.2006.02.003]. Appl.
Soft Comput., 7(3):
807-817.
[16] Golany, B., & Kress, M. (1993). A multicriteria
evaluation of the methods for
obtaining
weights from ratio-scale matrices. European Journal of
Operational Research, 69, 210
220.
[17] Mikhailov, L., & Singh, M. G. (1999). Comparison
analysis of methods for
deriving priorities
in the analytic hierarchy process. In IEEE International
Conference on Systems,
Man,and Cybernetics (Vol. 1, pp. 1037-1042 ). Tokyo.
[18] Saaty, T. (1994). Highlights and critical points in the
theory and application of
the Analytic Hierarchy Process. European Journal of Operational
Research, 74, 426-
447.
[19] Sha DY and Che ZH (2006). Supply chain network design:
partner selection
and production/distribution planning using a systematic model. J
Opl res Soc 57(1):
52-62.
[20] Nydick, Robert L. Hill, Ronald Paul Using the Analytic
Hierarchy Process to
Structure the Supplier Selection Procedure. International
Journal of Purchasing &
Materials Management. 28(2): pp. 31-36. (1992).