See

discussions, stats, and author profiles for this publication at:

https://www.researchgate.net/publication/223336524

A fuzzy approach for supplier evaluation

and selection in supply chain
management. International Journal of
Production...
Article in International Journal of Production Economics August 2006
DOI: 10.1016/j.ijpe.2005.03.009

CITATIONS

READS

638

2,650

3 authors, including:
Ching-Torng Lin
Da-Yeh University
25 PUBLICATIONS 1,365 CITATIONS
SEE PROFILE

Some of the authors of this publication are also working on these related projects:
To explore the behavior of enterprise to participate in Corporate Social Responsibility
(CSR). to do a same investigate in your country. then we can make a comparsion study.
View project

All content following this page was uploaded by Ching-Torng Lin on 23 April 2015.

The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document
and are linked to publications on ResearchGate, letting you access and read them immediately.

ARTICLE IN PRESS

Int. J. Production Economics 102 (2006) 289301

www.elsevier.com/locate/ijpe

A fuzzy approach for supplier evaluation and selection

in supply chain management
Chen-Tung Chena,, Ching-Torng Linb, Sue-Fn Huangb
a

Department of Information Management, National United University, 1, Lien Da, Kung-Ching Li, Miao-Li, Taiwan
b
Department of Information Management, Da-Yeh University, 112, Shan-Jiau Road, Da-Tsuen, Changhua, Taiwan
Received 14 April 2003; accepted 29 March 2005
Available online 25 May 2005

Abstract
This paper is aimed to present a fuzzy decision-making approach to deal with the supplier selection problem in supply
chain system. During recent years, how to determine suitable suppliers in the supply chain has become a key strategic
consideration. However, the nature of these decisions usually is complex and unstructured. In general, many
quantitative and qualitative factors such as quality, price, and exibility and delivery performance must be considered
to determine suitable suppliers. In this paper, linguistic values are used to assess the ratings and weights for these
factors. These linguistic ratings can be expressed in trapezoidal or triangular fuzzy numbers. Then, a hierarchy multiple
criteria decision-making (MCDM) model based on fuzzy-sets theory is proposed to deal with the supplier selection
problems in the supply chain system. According to the concept of the TOPSIS, a closeness coefcient is dened to
determine the ranking order of all suppliers by calculating the distances to the both fuzzy positive-ideal solution (FPIS)
and fuzzy negative-ideal solution (FNIS) simultaneously. Finally, an example is shown to highlight the procedure of the
proposed method at the end of this paper. This paper shows that the proposed model is very well suited as a decisionmaking tool for supplier selection decisions.
r 2005 Elsevier B.V. All rights reserved.
Keywords: Supplier selection; Supply chain; Linguistic variables; Fuzzy set theory; MCDM

1. Introduction
Recently, supply chain management and the
supplier (vendor) selection process have received
considerable attention in the business-management
Corresponding author. Tel.: +886 37 381833;

fax: +886 37 330776.

E-mail address: ctchen@nuu.edu.tw (C.-T. Chen).

literature. During the 1990s, many manufacturers

seek to collaborate with their suppliers in order to
upgrade their management performance and competitiveness (Ittner et al., 1999; Shin et al., 2000). The
material ow in a supply chain is shown in Fig. 1.
The purchasing function is increasingly seen as a
strategic issue in organizations. Buyer and supplier
relationships in manufacturing enterprises have
received a great deal of attention. When it is built

0925-5273/$ - see front matter r 2005 Elsevier B.V. All rights reserved.
doi:10.1016/j.ijpe.2005.03.009

ARTICLE IN PRESS
290

C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

Direct
Supplier

Direct
Supplier

Distributor

Consumer

Distributor
Direct
Supplier

Manufacturer /
Company

Consumer

Fig. 1. Material ow in supply chain.

on long-term relationships, a companys supply

chain creates one of the strongest barriers to entry
for competitors (Briggs, 1994; Choi and Hartley,
1996). In other words, once a supplier becomes
part of a well-managed and established supply
chain, this relationship will have a lasting effect on
the competitiveness of the entire supply chain.
Therefore, the supplier selection problem has
become one of the most important issues for
establishing an effective supply chain system. The
overall objective of supplier selection process is to
reduce purchase risk, maximize overall value to
the purchaser, and build the closeness and longterm relationships between buyers and suppliers
(Monczka et al., 1998).
In supply chains, coordination between a
manufacturer and suppliers is typically a difcult
and important link in the channel of distribution. Many models have been developed for
supplier selection decisions are based on rather
simplistic perceptions of decision-making process
(Boer et al., 1998; Lee et al., 2001). Most of these
methods do not seem to address the complex and
unstructured nature and context of many presentday purchasing decisions (Boer et al., 1998). In
fact, many existing decision models only quantities
criteria are considered for supplier selection.
However, several inuence factors are often not
taken into account in the decision making process,
such as incomplete information, additional qualitative criteria and imprecision preferences. According to the vast literature on supplier selection
(Boer et al., 1998; Choi and Hartley, 1996; Weber
et al., 1991), we conclude that some properties are
worth considering when solving the decisionmaking problem for supplier selection. First, the
criteria may consider quantitative as well as

qualitative dimensions (Choi and Hartley, 1996;

Dowlatshahi, 2000; Verma and Pullman, 1998;
Weber et al., 1991, 1998). In general, these
objectives among these criteria are conicted. A
strategic approach towards supplier selection may
further emphasize the need to consider multiple
criteria (Donaldson, 1994; Ellram, 1992; Swift,
1995). Second, several decision-makers are very
often involved in the decision process for supplier
selection (Boer et al., 1998). Third, decisionmaking is often inuenced by uncertainty in
practice. An increasing number of supplier decisions can be characterized as dynamic and
unstructured. Situations are changing rapidly or
are uncertain and decision variables are difcult or
impossible to quantify (Cook, 1992). Fourth, the
types of decision models can be divided into
compensatory and non-compensatory methods
(Boer et al., 1998; Ghodsypour and OBrien,
1998; Roodhooft and Konings, 1996). The compensatory decision models leading to an optimal
solution for dealing with supplier selection problems. The non-compensatory methods are that
use a score of an alternative on a particular
criterion can be compensated by high scores on
other criteria. From the literature it can be
concluded that in supplier selection the classic
concept of optimality may not always be the
most appropriate model (Boer et al., 1998). Overall speaking, we can conclude that supplier
selection may involve several and different types
of criteria, combination of different decision
models, group decision-making and various forms
of uncertainty. It is difcult to nd the best way to
evaluate and select supplier, and companies use a
variety of different methods to deal with it.
Therefore, the most important issue in the process

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

of supplier selection is to develop a suitable

method to select the right supplier.
In essential, the supplier selection problem in
supply chain system is a group decision-making
under multiple criteria. The degree of uncertainty,
the number of decision makers and the nature of
the criteria those have to be taken into account in
solving this problem. In classical MCDM methods,
the ratings and the weights of the criteria are known
precisely (Delgado et al., 1992; Hwang and Yoon,
1981; Kaufmann and Gupta, 1991). A survey of the
methods has been presented in Hwang and Yoon
(1981). Technique for Order Performance by
Similarity to Ideal Solution (TOPSIS), one of the
known classical MCDM methods, may provide the
basis for developing supplier selection models that
can effectively deal with these properties. It bases
upon the concept that the chosen alternative should
have the shortest distance from the Positive Ideal
Solution (PIS) and the farthest from the Negative
Ideal Solution (NIS).
Under many conditions, crisp data are inadequate
to model real-life situations. Since human judgements including preferences are often vague and
cannot estimate his preference with an exact
numerical value. A more realistic approach may
be to use linguistic assessments instead of numerical
values. In other words, the ratings and weights of
the criteria in the problem are assessed by means of
linguistic variables (Bellman and Zadeh, 1970;
Chen, 2000; Delgado et al., 1992; Herrera et al.,
1996; Herrera and Herrera-Viedma, 2000). In this
paper, we further extended to the concept of
TOPSIS to develop a methodology for solving
supplier selection problems in fuzzy environment
(Chen, 2000). Considering the fuzziness in the
decision data and group decision-making process,
linguistic variables are used to assess the weights of
all criteria and the ratings of each alternative with
respect to each criterion. We can convert the
decision matrix into a fuzzy decision matrix and
construct a weighted-normalized fuzzy decision
matrix once the decision-makers fuzzy ratings have
been pooled. According to the concept of TOPSIS,
we dene the fuzzy positive ideal solution (FPIS)
and the fuzzy negative ideal solution (FNIS). And
then, a vertex method is applied in this paper to
calculate the distance between two fuzzy ratings.

291

Using the vertex method, we can calculate the

distance of each alternative from FPIS and FNIS,
respectively. Finally, a closeness coefcient of each
alternative is dened to determine the ranking order
of all alternatives. The higher value of closeness
coefcient indicates that an alternative is closer to
FPIS and farther from FNIS simultaneously.
The paper is organized as follows. Next section
introduces the basic denitions and notations of
the fuzzy numbers and linguistic variables. In
Section 3, we present a fuzzy decision-making
method to cope with the supplier selection
problem. And then, the proposed method is
illustrated with an example. Finally, some conclusions are pointed out at the end of this paper.

2. Fuzzy numbers and linguistic variables

In this section, some basic denitions of fuzzy
sets, fuzzy numbers and linguistic variables are
reviewed from Buckley (1985), Kaufmann and
Gupta (1991), Negi (1989), Zadeh (1975). The
basic denitions and notations below will be used
throughout this paper until otherwise stated.
Denition 2.1. A fuzzy set A~ in a universe of
discourse X is characterized by a membership
function mA~ x which associates with each element
x in X a real number in the interval [0,1]. The
function value mA~ x is termed the grade of membership of x in A~ (Kaufmann and Gupta, 1991).

Denition 2.2. A fuzzy set A~ in the universe of

discourse X is convex if and only if
mA~ lx1 1
lx2 X minmA~ x1 ; mA~ x2

(1)

for all x1 ; x2 in X and all l 2 0; 1, where min

denotes the minimum operator (Klir and Yuan,
1995).

Denition 2.3. The height of a fuzzy set is the

largest membership grade attained by any element
in that set. A fuzzy set A~ in the universe of
discourse X is called normalized when the height
of A~ is equal to 1 (Klir and Yuan, 1995).

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

292

Denition 2.4. A fuzzy number is a fuzzy subset in

the universe of discourse X that is both convex and
normal. Fig. 2 shows a fuzzy number n~ in the
universe of discourse X that conforms to this
denition (Kaufmann and Gupta, 1991).

~n (x)

Denition 2.5. The a-cut of fuzzy number n~ is

dened as
n~ a fxi : mn~ xi Xa; xi 2 X g,

(2)
0

where a 2 0; 1.
The symbol n~ a represents a non-empty bounded
interval contained in X, which can be denoted by
n~ a nal ; nau , nal and nau are the lower and upper
bounds of the closed interval, respectively (Kaufmann and Gupta, 1991; Zimmermann, 1991). For
~ if nal 40 and nau p1 for all
a fuzzy number n,
a 2 0; 1, then n~ is called a standardized (normalized) positive fuzzy number (Negi, 1989).
Denition 2.6. A positive trapezoidal fuzzy number (PTFN) n~ can be dened as n1 ; n2 ; n3 ; n4 ,
shown in Fig. 3. The membership function, mn~ x is
dened as (Kaufmann and Gupta, 1991)
8
0;
xon1 ;
>
>
> x
n1
>
>
;
n
1 pxpn2 ;
>
< n2
n1
n2 pxpn3 ;
(3)
mn~ x 1;
>
>
x
n
4
>
n3 pxpn4 ;
>
n3
n4 ;
>
>
:
0;
x4n4 :
For a trapezoidal fuzzy number n~ n1 ; n2 ; n3 ; n4 ,
if n2 n3 , then n~ is called a triangular fuzzy
number. A non-fuzzy number r can be expressed

n1

n2

n3

n4

~
Fig. 3. Trapezoidal fuzzy number n.

as (r, r, r, r). By the extension principle (Dubois

and Prade, 1980), the fuzzy sum  and fuzzy
subtraction  of any two trapezoidal fuzzy
numbers are also trapezoidal fuzzy numbers; but
the multiplication  of any two trapezoidal fuzzy
numbers is only an approximate trapezoidal fuzzy
number. Given any two positive trapezoidal fuzzy
~ m1 ; m2 ; m3 ; m4 , n~ n1 ; n2 ; n3 ; n4
numbers, m
and a positive real number r, some main opera~ and n~ can be expressed
tions of fuzzy numbers m
as follows:
~  n~ m1 n1 ; m2 n2 ; m3 n3 ; m4 n4 ,
m

(4)

~  n~ m1
n4 ; m2
n3 ; m3
n2 ; m4
n1 ;
m

(5)

~  r m1 r; m2 r; m3 r; m4 r,
m

(6)

~  n~ m1 n1 ; m2 n2 ; m3 n3 ; m4 n4 .
m

(7)

~ is called a fuzzy matrix

Denition 2.7. A matrix D
if at least one element is a fuzzy number (Buckley,
1985).

~n (x)

0
~
Fig. 2. Fuzzy number n.

Denition 2.8. A linguistic variable is a variable

whose values are expressed in linguistic terms
(Zimmermann, 1991).
The concept of a linguistic variable is very
useful in dealing with situations, which are too
complex or not well dened to be reasonably
described in conventional quantitative expressions

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

(Zimmermann, 1991). For example, weight is a

linguistic variable whose values are very low, low,
medium, high, very high, etc. Fuzzy numbers can
also represent these linguistic values.
~ m1 ; m2 ; m3 ; m4 and n~ n1 ; n2 ; n3 ; n4
Let m
be two trapezoidal fuzzy numbers. Then the
distance between them can be calculated by using
the vertex method as (Chen, 2000)
~ n
~
d v m;

r
1

m1
n1 2 m2
n2 2 m3
n3 2 m4
n4 2 .
4

linguistic assessments (Delgado et al., 1998;

Herrera et al., 1996; Herrera and Herrera-Viedma,
2000). These linguistic variables can be expressed
in positive trapezoidal fuzzy numbers, as in Figs. 4
and 5. The importance weight of each criterion can
be by either directly assigning or indirectly using
pairwise comparison (Cook, 1992). It is suggested
in this paper that the decision-makers use the
linguistic variables shown in Figs. 4 and 5 to
evaluate the importance of the criteria and the
ratings of alternatives with respect to qualitative
criteria. For example, the linguistic variable
Medium High (MH) can be represented as
0:5; 0:6; 0:7; 0:8, the membership function of

~ m1 ; m2 ; m3 and n~ n1 ; n2 ; n3 be two
Let m
triangular fuzzy numbers. Then the distance
between them can be calculated by using the
vertex method as (Chen, 2000)

Very Low

Medium Low

Low (L)

~ n
~
d v m;
r
1
m1
n1 2 m2
n2 2 m3
n3 2 .

293

Medium High

Medium (M)

Very High
High (H)

9
The vertex method is an effective and simple
method to calculate the distance between two
trapezoidal fuzzy numbers. According to the
~
vertex method, two trapezoidal fuzzy numbers m
~ n
~ 0. Let
and n~ are identical if and only if d v m;
~ n~ and p~ be three trapezoidal fuzzy numbers.
m,
~ than
Fuzzy number n~ is closer to fuzzy number m
the other fuzzy number p~ if and only if
~ nod
~
~ p
~ (Chen, 2000).
d v m;
v m;

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

Fig. 4. Linguistic variables for importance weight of each

criterion.

Very Poor

Medium Poor

Poor (P)

3. Proposed method for supplier selection

Medium Good
Fair (F)

Very Good
Good (G)

A systematic approach to extend the TOPSIS is

proposed to solve the supplier-selection problem
under a fuzzy environment in this section. In this
paper the importance weights of various criteria
and the ratings of qualitative criteria are considered as linguistic variables. Because linguistic
assessments merely approximate the subjective
judgment of decision-makers, we can consider
linear trapezoidal membership functions to be
adequate for capturing the vagueness of these

Fig. 5. Linguistic variables for ratings.

10

ARTICLE IN PRESS
294

C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

which is

where

8
0;
>
>
>
> x
0:5 ;
>
>
< 0:6
0:5
mMedium High x 1;
>
>
x
0:8
>
>
0:7
0:8 ;
>
>
:
0;

xo0:5;
0:5pxp0:6;
0:6pxp0:7;

a minfak g;
k

(10)

0:7pxp0:8;
x40:8:

The linguistic variable Very Good (VG) can be

represented as (8,9,9,10), the membership function
of which is
8
xo8;
>
< 0;
x
8
;
8pxp9;
mVery Good x 9
8
(11)
>
: 1;
9pxp10:

K
1 X
ck ;
K k1

K
1 X
bk ,
K k1

d maxfd k g.
k

Let the fuzzy rating and importance weight of

the kth decision maker be x~ ijk aijk ; bijk ; cijk ; d ijk
and w~ jk wjk1 ; wjk2 ; wjk3 ; wjk4 ; i 1; 2; . . . ; m,
j 1; 2; . . . ; n, respectively. Hence, the aggregated
fuzzy ratings (x~ ij ) of alternatives with respect to
each criterion can be calculated as
x~ ij aij ; bij ; cij ; d ij

(13)

where
K
1 X
bijk ,
K k1

In fact, supplier selection in supply chain system

is a group multiple-criteria decision-making
(GMCDM) problem, which may be described by
means of the following sets:

aij minfaijk g;

(i) a set of K decision-makers called E fD1 ;

D2 ; . . . ; DK g;
(ii) a set of m possible suppliers called A fA1 ;
A2 ; . . . ; Am g;
(iii) a set of n criteria, C fC 1 ; C 2 ; . . . ; C n g, with
which supplier performances are measured;
(iv) a set of performance ratings of Ai i 1; 2; . . . ;
m with respect to criteria C j j 1; 2; . . . ; n,
called X fxij ; i 1; 2; . . . ; m; j 1; 2; . . . ; ng.

The aggregated fuzzy weights (w~ j ) of each

criterion can be calculated as

Assume that a decision group has K decision

makers, and the fuzzy rating of each decisionmaker Dk k 1; 2; . . . ; K can be represented as a
positive trapezoidal fuzzy number R~ k k 1; 2; . . . ;
K with membership function mR~ k x. A good
aggregation method should be considered the
range of fuzzy rating of each decision-maker. It
means that the range of aggregated fuzzy rating
must include the ranges of all decision-makers
fuzzy ratings. Let the fuzzy ratings of all decisionmakers be trapezoidal fuzzy numbers R~ k ak ; bk ;
ck ; d k , k 1; 2; . . . ; K. Then the aggregated fuzzy
rating can be dened as
R~ a; b; c; d;

k 1; 2; . . . ; K

(12)

cij

K
1 X
cijk ;
K k1

bij

d ij maxfd ijk g.
k

w~ j wj1 ; wj2 ; wj3 ; wj4 ,

(14)

where
wj1 minfwjk1 g;
k

wj3

K
1 X
wjk3 ;
K k1

wj2

K
1 X
wjk2 ,
K k1

wj4 maxfwjk4 g.
k

As stated above, a supplier-selection problem

can be concisely expressed in matrix format as
follows:
3
2
x~ 11 x~ 12 ::::: x~ 1n
7
6
6 x~ 21 x~ 22 ::::: x~ 2n 7
7
6
~ 6
7
D
..
.. 7,
6 ..
6 .
.
:::::
. 7
5
4
x~ m1 x~ m2 ::::: x~ mn
~ w~ 1 ; w~ 2 ; . . . w~ n ,
W
where x~ ij aij ; bij ; cij ; d ij and w~ j wj1 ; wj2 ; wj3 ;
wj4 ; i 1; 2; . . . ; m, j 1; 2; . . . ; n can be approximated by positive trapezoidal fuzzy numbers.

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

To avoid complexity of mathematical operations in a decision process, the linear scale

transformation is used here to transform the
various criteria scales into comparable scales.
The set of criteria can be divided into benet
criteria (the larger the rating, the greater
the preference) and cost criteria (the smaller the
rating, the greater the preference). Therefore, the
normalized fuzzy-decision matrix can be represented as

295

where
v~j maxfvij4 g
i

and

v~

j minfvij1 g,
i

i 1; 2; . . . ; m; j 1; 2; . . . ; n.
The distance of each alternative (supplier) from
A and A
can be currently calculated as
d i

n
X

d v ~vij ; v~j ;

i 1; 2; . . . ; m,

(19)

j1

~ ~rij mn ,
R

(15)

where B and C are the sets of benet criteria and

cost criteria, respectively, and
!
aij bij cij d ij
r~ij
; ; ;
; j 2 B;
d j d j d j d j





aj aj aj aj
; ; ;
; j 2 C;
r~ij
d ij cij bij aij
d j max d ij ;

j 2 B;

a

j min aij ;

j 2 C:

The normalization method mentioned above is

designed to preserve the property in which the
elements r~ij ; 8i; j are standardized (normalized)
trapezoidal fuzzy numbers.
Considering the different importance of each
criterion, the weighted normalized fuzzy-decision
matrix is constructed as
V~ ~vij mn;

i 1; 2; . . . ; m;

j 1; 2; . . . ; n,
(16)

where
v~ij r~ij w~ j .
According to the weighted normalized fuzzydecision matrix, normalized positive trapezoidal
fuzzy numbers can also approximate the elements
v~ij ; 8i; j. Then, the fuzzy positive-ideal solution
(FPIS, A ) and fuzzy negative-ideal solution
(FNIS, A
) can be dened as
A ~v1 ; v~2 ; . . . ; v~n ,

(17)

A
~v

1 ; v~2 ; . . . ; v~n ,

(18)

d

i

n
X

d v ~vij ; v~

j ;

i 1; 2; . . . ; m,

(20)

j1

where d v ; is the distance measurement between

two fuzzy numbers.
A closeness coefcient is dened to determine
the ranking order of all possible suppliers once d i
and d

i of each supplier Ai i 1; 2; . . . ; m has
been calculated. The closeness coefcient represents the distances to the fuzzy positive-ideal
solution (A ) and the fuzzy negative-ideal solution
(A
) simultaneously by taking the relative closeness to the fuzzy positive-ideal solution. The
closeness coefcient (CCi ) of each alternative
(supplier) is calculated as
CCi

d i

d

i
;
d

i

i 1; 2; . . . ; m.

(21)

It is clear that CCi 1 if Ai A and CCi 0 if

Ai A
. In other words, supplier Ai is closer to
the FPIS (A ) and farther from FNIS (A
) as CCi
approaches to 1. According to the descending
order of CCi , we can determine the ranking order
of all suppliers and select the best one from among
a set of feasible suppliers. Although we can
determine the ranking order of all feasible
suppliers, a more realistic approach may be to
use a linguistic variable to describe the current
assessment status of each supplier in accordance
with its closeness coefcient. In order to describe
the assessment status of each supplier, we divide
the interval [0,1] into ve sub-intervals. Five
linguistic variables with respect to the sub-intervals
are dened to divide the assessment status of
supplier into ve classes. The decision rules of the

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

296
Table 1
Approval status
Closeness coefcient (CCi )
CCi
CCi
CCi
CCi
CCi

2 0; 0:2
2 0:2; 0:4
2 0:4; 0:6
2 0:6; 0:8
2 0:8; 1:0

Assessment status
Do not recommend
Recommend with high risk
Recommend with low risk
Approved
Approved and preferred

ve classes are shown in Table 1. According to the

Table 1, it means that
If CCi 2 0; 0:2, then supplier Ai belongs to
Class I and the assessment status of supplier Ai
is not recommend;
If CCi 2 0:2; 0:4, then supplier Ai belongs to
Class II and the assessment status of supplier Ai
is recommend with high risk;
If CCi 2 0:4; 0:6, then supplier Ai belongs to
Class III and the assessment status of supplier
Ai is recommend with low risk;
If CCi 2 0:6; 0:8, then supplier Ai belongs to
Class IV and the assessment status of supplier
Ai is approved;
If CCi 2 0:8; 1:0, then supplier Ai belongs to
Class V and the assessment status of supplier Ai
is approved and preferred to recommend.
According to Table 1 and decision rules, we can
use a linguistic variable to describe the current
assessment status of each supplier. In addition, if
any two suppliers belong to the same class of
assessment status, the closeness coefcient value is
used to determine their rank.
In summation, an algorithm of the fuzzy
decision-making method for dealing with the
supplier selection is given as follows.
Step 1: Form a committee of decision-makers,
and then identify the evaluation criteria.
Step 2: Choose the appropriate linguistic variables for the importance weight of the criteria and
the linguistic ratings for suppliers.
Step 3: Aggregate the weight of criteria to get
the aggregated fuzzy weight w~ j of criterion C j , and
pool the decision-makers ratings to get the
aggregated fuzzy rating x~ ij of supplier Ai under
criterion C j .

Step 4: Construct the fuzzy-decision matrix and

the normalized fuzzy-decision matrix.
Step 5: Construct weighted normalized fuzzydecision matrix.
Step 6: Determine FPIS and FNIS.
Step 7: Calculate the distance of each supplier
from FPIS and FNIS, respectively.
Step 8: Calculate the closeness coefcient of
each supplier.
Step 9: According to the closeness coefcient, we
can understand the assessment status of each
supplier and determine the ranking order of all
suppliers.

4. Numerical example
A high-technology manufacturing company
desires to select a suitable material supplier to
purchase the key components of new products.
After preliminary screening, ve candidates (A1 ,
A2 , A3 , A4 , A5 ) remain for further evaluation. A
committee of three decision-makers, D1 ; D2 and
D3 , has been formed to select the most suitable
supplier. Five benet criteria are considered:
(1)
(2)
(3)
(4)
(5)

protability of supplier (C1),

relationship closeness (C 2 ),
technological capability (C 3 ),
conformance quality (C 4 ),
conict resolution (C 5 ).

The hierarchical structure of this decision problem

is shown in Fig. 6. The proposed method is
currently applied to solve this problem, the
computational procedure of which is summarized
as follows:
Step 1: Three decision-makers use the linguistic
weighting variables shown in Fig. 4 to assess the
importance of the criteria. The importance weights
of the criteria determined by these three decisionmakers are shown in Table 2.
Step 2: Three decision-makers use the linguistic
rating variables shown in Fig. 5 to evaluate the
ratings of candidates with respect to each criterion.
The ratings of the ve candidates by the decisionmakers under the various criteria are shown in
Table 3.

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

297

Goal

C2

C3

C4

C5

Profitability

Relationship

Technological

Conformance

Conflict

of supplier

closeness

capability

quality

resolution

C11

A1

A2

A3

A4

A5

Fig. 6. Hierarchical structure of decision problem.

Table 2
Importance weight of criteria from three decision-makers
Criteria

Table 3
Ratings of the ve candidates by decision-makers under various
criteria

Decision-makers
Criteria

C1
C2
C3
C4
C5

D1

D2

D3

H
VH
VH
H
H

H
VH
VH
H
H

H
VH
H
H
H

C1

C2

Step 3: Then the linguistic evaluations shown in

Tables 2 and 3 are converted into trapezoidal fuzzy
numbers to construct the fuzzy-decision matrix
and determine the fuzzy weight of each criterion,
as in Table 4.
Step 4: The normalized fuzzy-decision matrix is
constructed as in Table 5.
Step 5: Weighted normalized fuzzy-decision
matrix is constructed as in Table 6.
Step 6: Determine FPIS and FNIS as
A 0:9; 0:9; 0:9; 0:9; 1; 1; 1; 1; 1; 1; 1; 1; 0:9;
0:9; 0:9; 0:9; 0:9; 0:9; 0:9; 0:9,
A
0:35; 0:35; 0:35; 0:35; 0:4; 0:4; 0:4; 0:4;
0:35; 0:35; 0:35; 0:35; 0:35; 0:35; 0:35; 0:35; 0:35;
0:35; 0:35; 0:35.

C3

C4

C5

Suppliers

A1
A2
A3
A4
A5
A1
A2
A3
A4
A5
A1
A2
A3
A4
A5
A1
A2
A3
A4
A5
A1
A2
A3
A4
A5

Decision-makers
D1

D2

D3

MG
G
VG
G
MG
MG
VG
VG
G
MG
G
VG
VG
MG
MG
G
G
VG
G
MG
G
VG
G
G
MG

MG
G
VG
G
MG
MG
VG
G
G
G
G
VG
VG
MG
MG
G
VG
VG
G
MG
G
VG
VG
G
MG

MG
G
G
G
MG
VG
VG
G
MG
G
G
VG
G
G
MG
G
VG
VG
G
G
G
VG
G
VG
MG

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

298

Table 4
Fuzzy-decision matrix and fuzzy weights of ve candidates

A1
A2
A3
A4
A5
Weight

C1

C2

C3

C4

C5

(5,6,7,8)
(7,8,8,9)
(7,8.7,9.3,10)
(7,8,8,9)
(5,6,7,8)
(0.7,0.8,0.8,0.9)

(5,7,8,10)
(8,9,10,10)
(7,8.3,8.7,10)
(5,7.3,7.7,9)
(5,7.3,7.7,9)
(0.8,0.9,1.0,1.0)

(7,8,8,9)
(8,9,10,10)
(7,8.7,9.3,10)
(5,6.7,7.3,9)
(5,6,7,8)
(0.7,0.87,0.93,1.0)

(7,8,8,9)
(7,8.7,9.3,10)
(8,9,10,10)
(7,8,8,9)
(5,6.7,7.3,9)
(0.7,0.8,0.8,0.9)

(7,8,8,9)
(8,9,10,10)
(7,8.3,8.7,10)
(7,8.3,8.7,10)
(5,6,7,8)
(0.7,0.8,0.8,0.9)

Table 5
Normalized fuzzy-decision matrix

A1
A2
A3
A4
A5

C1

C2

C3

C4

C5

(0.5,0.6,0.7,0.8)
(0.7,0.8,0.8,0.9)
(0.7,0.87,0.93,1)
(0.7,0.8,0.8,0.9)
(0.5,0.6,0.7,0.8)

(0.5,0.7,0.8,1)
(0.8,0.9,1,1)
(0.7,0.83,0.87,1)
(0.5,0.73,0.77,0.9)
(0.5,0.73,0.77,0.9)

(0.7,0.8,0.8,0.9)
(0.8,0.9,1,1)
(0.7,0.87,0.93,1)
(0.5,0.67,0.73,0.9)
(0.5,0.6,0.7,0.8)

(0.7,0.8,0.8,0.9)
(0.7,0.87,0.93,1)
(0.8,0.9,1,1)
(0.7,0.8,0.8,0.9)
(0.5,0.67,0.73,0.9)

(0.7,0.8,0.8,0.9)
(0.8,0.9,1,1)
(0.7,0.83,0.87,1)
(0.7,0.83,0.87,1)
(0.5,0.6,0.7,0.8)

Table 6
Weighted normalized fuzzy-decision matrix

A1
A2
A3
A4
A5

C1

C2

C3

C4

C5

(0.35,0.48,0.56,0.72)
(0.49,0.64,0.64,0.81)
(0.49,0.7,0.74,0.9)
(0.49,0.64,0.64,0.81)
(0.35,0.48,0.56,0.72)

(0.4,0.63,0.8,1)
(0.64,0.81,1,1)
(0.56,0.75,0.87,1)
(0.4,0.66,0.77,0.9)
(0.4,0.66,0.77,0.9)

(0.49,0.7,0.74,0.9)
(0.56,0.78,0.93,1)
(0.49,0.76,0.86,1)
(0.35,0.58,0.68,0.9)
(0.35,0.52,0.65,0.8)

(0.49,0.64,0.64,0.81)
(0.49,0.7,0.74,0.9)
(0.56,0.72,0.8,0.9)
(0.49,0.64,0.64,0.81)
(0.35,0.54,0.58,0.81)

(0.49,0.64,0.64,0.81)
(0.56,0.72,0.8,0.9)
(0.49,0.66,0.7,0.9)
(0.49,0.66,0.7,0.9)
(0.35,0.48,0.56,0.72)

Step 7: Calculate the distance of each supplier

from FPIS and FNIS with respect to each
criterion, respectively, as Tables 7 and 8.
Step 8: Calculate d i and d

i of ve possible
suppliers Ai i 1; 2; . . . ; 5 as Table 9.
Step 9: Calculate the closeness coefcient of
each supplier as
CC1 0:50;

CC2 0:64;

CC4 0:51;

CC5 0:40.

CC3 0:62,

Step 10: According to the closeness coefcients

of ve suppliers and the approval status level, we
know that suppliers A2 and A3 belong to Class IV,

Table 7
Distances between Ai i 1; 2; . . . ; 5 and A with respect to
each criterion

d(A1,A*)
d(A2,A*)
d(A3,A*)
d(A4,A*)
d(A5,A*)

C1

C2

C3

C4

C5

0.4
0.28
0.24
0.28
0.4

0.37
0.2
0.26
0.37
0.37

0.33
0.25
0.29
0.42
0.45

0.28
0.24
0.2
0.28
0.37

0.28
0.2
0.26
0.26
0.4

the assessment status of which are Approved.

Suppliers A1 , A4 and A5 belong to Class III. This
means that their assessment status is Recommend

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301
Table 8
Distances between Ai i 1; 2; . . . ; 5 and A
with respect to
each criterion

d(A1,A )
d(A2,A
)
d(A3,A
)
d(A4,A
)
d(A5,A
)

C1

C2

C3

C4

C5

0.22
0.32
0.39
0.32
0.22

0.38
0.49
0.43
0.34
0.34

0.39
0.5
0.47
0.34
0.28

0.32
0.39
0.41
0.32
0.27

0.32
0.41
0.37
0.37
0.22

Very Low
Low (L)

A1
A2
A3
A4
A5

d

i

d i d

i

CCi

1.66
1.17
1.25
1.61
1.99

1.63
2.11
2.07
1.69
1.33

3.29
3.28
3.32
3.3
3.32

0.5
0.64
0.62
0.51
0.4

Medium High

Medium (M)

Very High
High (H)

Table 9
Computations of d i , d

i and CCi
d i

Medium Low

299

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

Fig. 7. Alterative linguistic variables for importance weight of

each criterion.

Very Poor

Medium Poor

Poor (P)

Medium Good

Fair (F)

Very Good

Good (G)

with low risk. However, according to the closeness coefcients, supplier A2 is preferred to A3
because CC2 4CC3 in Class IV. In Class III, the
preferred order is A4 4A1 4A5 because CC4 4
CC1 4CC5 . Finally, the ranking order of ve
suppliers is fA2 4A3 g4fA4 4A1 4A5 g.
In the other case, the different membership
functions of linguistic variables are used to
compare the result of the ranking order. The
membership functions of linguistic variables are
triangular fuzzy numbers. Three decision-makers
use the linguistic variables shown in Figs. 7 and 8
to assess the importance of criteria and evaluate
the ratings of candidates with respect to each
criterion. Applying the computational procedure
of proposed method, the closeness coefcient of
each supplier can be calculated as
CC1 0:50;

CC2 0:64;

CC4 0:51;

CC5 0:40.

CC3 0:63,

According to the closeness coefcients, we know

that suppliers A2 and A3 belong to Class IV.
Suppliers A1 , A4 and A5 belong to Class III. The
ranking order of ve suppliers is fA2 4A3 g4
fA4 4A1 4A5 g. Obviously, the results of ranking

10

Fig. 8. Alterative linguistic variables for ratings.

order are identical when the different membership

functions of linguistic variables are used in the
proposed method. Therefore, it can conrm that
this proposed method is very effective to deal with
the problem of supplier selection.

5. Conclusions
Many practitioners and researchers have presented the advantages of supply chain management. In order to increase the competitive
advantage, many companies consider that a welldesigned and implemented supply chain system is
an important tool. Under this condition, building
on the closeness and long-term relationships
between buyers and suppliers is critical success

ARTICLE IN PRESS
300

C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301

factor to establish the supply chain system.

Therefore, supplier selection problem becomes
the most important issue to implement a successful
supply chain system.
In general, supplier selection problems adhere to
uncertain and imprecise data, and fuzzy-set theory
is adequate to deal with them. In a decisionmaking process, the use of linguistic variables in
decision problems is highly benecial when performance values cannot be expressed by means of
numerical values. In other words, very often, in
assessing of possible suppliers with respect to
criteria and importance weights, it is appropriate
to use linguistic variables instead of numerical
values. Due to the decision-makers experience,
feel and subjective estimates often appear in the
process of supplier selection problem, an extension
version of TOPSIS in a fuzzy environment is
proposed in this paper. The fuzzy TOPSIS method
can deal with the ratings of both quantitative as
well as qualitative criteria and select the suitable
supplier effectively. It appears from the foregoing
sections that fuzzy TOPSIS method may be a
useful additional tool for the problem of supplier
selection in supply chain system.
In fact, the fuzzy TOPSIS method is very
exible. According to the closeness coefcient,
we can determine not only the ranking order but
also the assessment status of all possible suppliers.
Signicantly, the proposed method provides more
objective information for supplier selection and
evaluation in supply chain system. The systematic
framework for supplier selection in a fuzzy
environment presented in this paper can be easily
extended to the analysis of other management
decision problems. However, improving the approach for solving supplier selection problems
more efciently and developing a group decisionsupport system in a fuzzy environment can be
considered as a topic for future research.

Acknowledgements
The authors gratefully acknowledge the nancial support of the National Science Council,
Taiwan, under project number NSC 92-2213-E212-008.

References
Bellman, B.E., Zadeh, L.A., 1970. Decision-making in a fuzzy
environment. Management Science 17 (4), 141164.
Briggs, P., 1994. Vendor assessment for partners in supply.
European Journal of Purchasing & Supply Management 1,
4959.
Buckley, J.J., 1985. Fuzzy hierarchical analysis. Fuzzy Sets and
Systems 17, 233247.
Chen, C.T., 2000. Extensions of the TOPSIS for group
decision-making under fuzzy environment. Fuzzy Sets and
Systems 114, 19.
Choi, T.Y., Hartley, J.L., 1996. An exploration of supplier
selection practices across the supply chain. Journal of
Operations Management 14, 333343.
Cook, R.L., 1992. Expert systems in purchasing applications
and development. International Journal of Purchasing and
Management 18, 2027.
de Boer, L., van der Wegen, L., Telgen, J., 1998. Outranking
methods in support of supplier selection. European Journal
of Purchasing & Supply Management 4, 109118.
Delgado, M., Verdegay, J.L., Vila, M.A., 1992. Linguistic
decision-making models. International Journal of Intelligent
Systems 7, 479492.
Delgado, M., Herrera, F., Herrera-Viedma, E., Martinez, L.,
1998. Combining numerical and linguistic information in
group decision making. Journal of Information Sciences
107, 177194.
Donaldson, B., 1994. Supplier selection criteria on the service
dimension. European Journal of Purchasing & Supply
Management 1, 209217.
Dowlatshahi, S., 2000. Designbuyersupplier interface:
Theory versus practice. International Journal of Production
Economics 63, 111130.
Dubois, D., Prade, H., 1980. Fuzzy Sets and Systems: Theory
and Applications. Academic Press Inc., New York.
Ellram, L.M., 1992. The supplier selection decision in strategic
partnerships. International Journal of Purchasing and
Management 18, 814.
Ghodsypour, S.H., OBrien, C., 1998. A decision support
system for supplier selection using an integrated analytic
hierarchy process and linear programming. International
Journal of Production Economics 5657, 199212.
Herrera, F., Herrera-Viedma, E., 2000. Linguistic decision
analysis: Steps for solving decision problems under linguistic information. Fuzzy Sets and Systems 115, 6782.
Herrera, F., Herrera-Viedma, E., Verdegay, J.L., 1996. A model
of consensus in group decision making under linguistic
assessments. Fuzzy Sets and Systems 78, 7387.
Hwang, C.L., Yoon, K., 1981. Multiple Attributes Decision
Making Methods and Applications. Springer, New York.
Ittner, C.D., Larcker, D.F., Nagar, V., Rajan, M.V., 1999.
Supplier selection, monitoring practices, and rm performance. Journal of Accounting and Public Policy 18, 253281.
Kaufmann, A., Gupta, M.M., 1991. Introduction to Fuzzy
Arithmetic: Theory and Applications. Van Nostrand Reinhold, New York.

ARTICLE IN PRESS
C.-T. Chen et al. / Int. J. Production Economics 102 (2006) 289301
Klir, G.J., Yuan, B., 1995. Fuzzy Sets and Fuzzy Logic: Theory
and Applications. Prentice-Hall Inc., USA.
Lee, E.K., Ha, S., Kim, S.K., Delgado, M., 2001. Supplier
selection and management system considering relationships
in supply chain management. IEEE Transactions on
Engineering Management 48 (3), 307318.
Monczka, R., Trent, R., Handeld, R., 1998. Purchasing and
Supply Chain Management. South-Western College Publishing, New York.
Negi, D.S., 1989. Fuzzy analysis and optimization. Ph.D.
Dissertation, Department of Industrial Engineering, Kansas
State University.
Roodhooft, F., Konings, J., 1996. Vendor selection and
evaluationan activity based costing approach. European
Journal of Operational Research 96, 97102.
Shin, H., Collier, D.A., Wilson, D.D., 2000. Supply management orientation and supplier/buyer performance. Journal
of Operations Management 18, 317333.

301

Swift, C.O., 1995. Preference for single sourcing and supplier selection criteria. Journal of Business Research 32,
105111.
Verma, R., Pullman, M.E., 1998. An analysis of the supplier
selection process. Omega 26, 739750.
Weber, C.A., Current, J.R., Benton, W.C., 1991. Vendor
selection criteria and methods. European Journal of
Operational Research 50, 218.
Weber, C.A., Current, J.R., Desai, A., 1998. Non-cooperative
negotiation strategies for vendor selection. European
Journal of Operational Research 108, 208223.
Zadeh, L.A., 1975. The concept of a linguistic variable and its
application to approximate reasoning. Information Sciences
8, 199249(I) 301357(II).
Zimmermann, H.J., 1991. Fuzzy Set Theory and its Applications, second ed. Kluwer Academic Publishers, Boston,
Dordrecht, London.