Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
INTRODUCTION
The vendor rating process is a critical step of the purchasing
function for any organization. Vendor rating systems identify top
---------------------------------
* Nicola Costantino, Ph.D., a Professor in Management, and Rector;
Mariagrazia Dotoli, Ph.D., an Assistant Professor in Control Systems
Engineering; Marco Falagario, Ph.D., a Contract Professor in Management;
and Maria Pia Fanti, Ph.D., an Associate Professor in Control Systems
Engineering, are at Politecnico of Bari. Prof. Costantino’s research interests
are in Supply Chain Management and Public Procurement. Prof. Dotoli’s
research interests are in Design, Optimization and Performance Evaluation
of Supply Chains, Dr. Falagario’s research interests are in Logistics,
Optimization Models and Public/Private Procurement, and Prof. Fanti’s
research interests are in Modelling, Identification and Fault Diagnosis of
Industrial Discrete Event Systems.
suppliers, i.e., the candidate partners that are best equipped to meet
the customer’s expected level of performance, and then check them
periodically (Baily, Farmer, Jessop, & Jones, 2005). Consequently, the
supplier or vendor selection process receives considerable attention
in business management literature (Bruno, Esposito, Genovese, &
Passaro, 2009; Chen, Yeh, & Yang, 2004; de Boer, Labro, &
Morlacchi, 2001; Huang & Keshar, 2007). Indeed, incorrect decisions
about supplier selection may lead to disruptions in the supply of
product/services, and therefore to serious troubles in the
organization operation (Piramuthu, 2005).
In most countries the public sector has recently started using
innovative methodologies for supplier selection (de Boer, Labro, &
Morlacchi, 2001; Panayiotou, Gayialis, & Tatsiopoulos, 2004; Erridge
& Callender, 2005). Some common points may be found between
procedures for supplier selection in the public and private sectors. In
a review of 74 articles Weber, Current, and Benton (1991) concluded
that by nature supplier selection is a multi-objective problem. Indeed,
both for private and public organizations vendor selection is a multi-
objective decision problem that besides the obvious goal of (low)
price includes conflicting objectives: quality, quantity, delivery,
performance, capacity, communication, service, geographical location
etc. (Araz & Ozkarahan, 2007; Degraeve, Labro, & Roodhooft, 2000;
Morlacchi, 1999).
Despite the similarities between private and governmental
purchasing, the latter type of procurement exhibits some peculiarities
(Panayiotou, Gayialis, & Tatsiopoulos, 2004). In most countries, the
public sector is covered by a number of public procurement
regulations, bringing legislative requirements into force: for instance,
in the European Union the 2004/18/EC Directive, also called the
Public Procurement Directive, is effective (The European Parliament,
2004). As a consequence, public procurement differs from private
procurement in the fact that prescribed procedures are to be followed
and transparency is imperative (Panayiotou, Gayialis, & Tatsiopoulos,
2004) for the so called public tender committee (usually a
commission of experts, named by the public authority) that exists to
perform the same duty as does the buyer of a private contract. In
other words, it is crucial that public procurement follows strict and
clear business models that optimize the specific service objectives
and considers the impact on processes across the considered
USING FUZZY DECISION MAKING FOR SUPPLIER SELECTION IN PUBLIC PROCUREMENT 405
METHODS
The Input Data
In the public procurement sector, governmental regulations
typically impose that all the potential suppliers satisfying the
requirements specified in the public tender call may bid; public
agencies have thus to evaluate and rank all the different bids,
according to a prefixed set of parameters (offered price, delivery time,
quality, etc.) in a transparent way and on the basis of strict
procedures. Accordingly, in the public procurement sector a vendor
selection decision problem can be defined through the set of bidding
suppliers S=s1,s2,…,sm and the given set of conflicting criteria
C=c1,c2,…,cn (defined beforehand by the tender committee) against
which vendors in S have to be ranked. Consequently, each supplier
siS is associated the following n-tuple: (di1, di2,…,din), where dij
represents the value of the performance index characterizing the i-th
vendor with i=1,…,m with respect to the j-th criterion with j=1,…,n. For
example, the first performance index di1 associated to the i-th
supplier with i=1,…,m typically represents the price of the received
bid. These performance indices are collected in a m×n decision
matrix D, where m is the number of available vendors and n is the
number of criteria. Therefore, the generic element dij of D, with
i=1,…,m and j=1,…,n, represents the j-th performance value of the i-th
alternative supplier. The decision problem data are completed by the
criteria importance, i.e., each criterion cj with j=1,…,n is associated
n
with a given weight wj, with w j 1 , assigned by the public tender
j 1
committee and specified in the call. It is noteworthy that soft
computing methods may be straightforwardly employed to address
the issue of obtaining in an automatic and objective way the criteria
weights. For instance, a fuzzy inference system with a knowledge
base containing “If…Then” rules (Zimmermann, 2001) may be set up
by the tender committee, with the eventual help of experts, to
automatically determine the weight assigned to the criteria.
USING FUZZY DECISION MAKING FOR SUPPLIER SELECTION IN PUBLIC PROCUREMENT 409
The Technique
The well-known fuzzy multi-objective technique, FAHP, (Saaty,
1990; Triantaphyllou & Lin, 1996) is proposed and evaluated in this
work for use in the decision problem of supplier selection for public
procurement. In FAHP, given the input data previously described, a
fuzzification process associates to each element dij with i=1,…,m and
j=1,…,n of D a fuzzy value d’ij, with d’ij[0,1] defining the m×n
fuzzified decision matrix D’ that models the committee’s satisfaction
degree with respect to the bidding suppliers against each criterion. In
particular, each j-th column of D’ for j=1,…,n is obtained by applying
to the corresponding column of D a fuzzy membership function μj with
j=1,…,n that is defined over the performance indices domain with
values in the [0,1] interval and mimics the tender committee
evaluation of the j-th performance index.
The fuzzification process enables the tender committee to
simultaneously take into account, in a transparent and rigorous way,
both quantitative and qualitative evaluation criteria, while fitting the
synthetic preference of the committee based on the chosen
membership functions’ shapes. Indeed, the choice of such functions
is subjective and has to be performed by the tender committee before
the award. If necessary, the membership function selection may take
place with the help of experts joining the committee for this purpose.
The definition of membership functions is a key point in the
fuzzification process, because the only restriction that a membership
function has to satisfy is that its values must be in the [0,1] range. A
fuzzy set can therefore, unlike a crisp one, be represented by an
infinite number of membership functions: a whole variety of
possibilities exists, including triangular, trapezoidal or Gaussian
membership functions, as well as sinusoidal, exponential shapes and
so forth (The Mathworks, Inc., 2004b). Figures 1 to 4 respectively
represent a linear, piece-wise linear, sigmoidal, and linear
membership function. The fact that a fuzzy set can be described by
an infinite number of membership functions is at the same time a
weakness and a strong point: uniqueness is sacrificed for the
advantage of flexibility, thus making the “adjustment” of a fuzzy
model possible. When fuzzy decision making is used in public
procurement, this subjectivity feature is an added value of fuzzy
decision making, since it allows close mimicking of the intuitive
tender committee behavior in the criteria evaluation. Note that in the
410 COSTANTINO, DOTOLI, FALAGARIO & PIA FANTI
FIGURE 1
An Example of Linear and Monotonically
Decreasing Membership Function
0.8
Degree of membership
0.6
0.4
0.2
FIGURE 2
An Example of Piece-Wise Linear Membership Function with a Local
Maximum
0.8
Degree of membership
0.6
0.4
0.2
0 5 10 15 20 25
Reduction time in the execution [weeks]
USING FUZZY DECISION MAKING FOR SUPPLIER SELECTION IN PUBLIC PROCUREMENT 411
FIGURE 3
An Example of Sigmoidal and Monotonically Increasing Membership
Function
0.8
Degree of membership
0.6
0.4
0.2
0 20 40 60 80 100 120
Free maintenance time [months]
FIGURE 4
An Example of Linear and Monotonically Increasing
Membership Function
0.8
Degree of membership
0.6
0.4
0.2
0 1 2 3 4 5 6 7 8 9 10
Enhancement plans score
412 COSTANTINO, DOTOLI, FALAGARIO & PIA FANTI
TABLE 1
Saaty’s Original AHP Scale
35 45
Pairwise 0 5 15 25 55 65 75
Differences 5 15 25 35 65 75 100
45 55
AHP Scale 1 2 3 4 5 6 7 8 9
Discussion
Usually, in most public tenders adopting a MEAT procedure the
top-ranked vendor is selected using the so-called Linear Weighting
(LW) technique (Dulmin & Mininno, 2004; Sonmez, 2006). Such an
approach is structurally compensatory and tends to counterbalance a
good performance against a criterion with a second-rate performance
index, which in many cases is not realistic: indeed, in private
USING FUZZY DECISION MAKING FOR SUPPLIER SELECTION IN PUBLIC PROCUREMENT 415
TABLE 2
Case Study Bids, Corresponding Decision Matrix Elements and Overall
Performance
Reduction in Free Overall
Enhance- perfor-
Vendor Price execution maintenance
ment plans mance
time post delivery
di2 di3
si di1 [€] di4 PIi_FAHP
[weeks] [months]
s1 110238.11 8.00 48.00 8.00 0.4243
s2 110963.63 4.00 9.00 9.00 0
s3 109514.93 20.00 29.00 1.00 0
s4 110484.45 8.00 15.00 9.00 0
s5 110681.87 13.00 22.00 6.00 0
s6 111092.92 4.00 29.00 1.00 0
s7 112930.37 15.00 50.00 3.00 0.4714
s8 112783.38 7.00 6.00 5.00 0
s9 131714.23 16.00 108.00 10.00 0
s10 109920.87 17.00 113.00 10.00 0.8069
s11 110821.52 19.00 59.00 2.00 0.4472
s12 109775.89 11.00 59.00 10.00 0.6835
s13 108511.70 2.00 41.00 10.00 0.2593
s14 111457.61 6.00 108.00 5.00 0.5657
USING FUZZY DECISION MAKING FOR SUPPLIER SELECTION IN PUBLIC PROCUREMENT 417
TABLE 2 (Continued)
Reduction in Free Overall
Enhance- perfor-
Vendor Price execution maintenance
ment plans mance
time post delivery
di2 di3
si di1 [€] di4 PIi_FAHP
[weeks] [months]
s15 111127.97 23.00 44.00 8.00 0.3300
s16 108990.13 4.00 13.00 1.00 0
s17 115299.67 21.00 94.00 4.00 0.3973
s18 111242.01 13.00 47.00 9.00 0.4007
s19 112036.06 25.00 29.00 8.00 0
s20 111461.96 2.00 48.00 10.00 0.3266
s21 111009.58 11.00 12.00 7.00 0
s22 110504.87 3.00 16.00 0.00 0
s23 110247.06 24.00 113.00 8.00 0.400
s24 110438.76 0.00 120.00 9.00 0
s25 112457.83 19.00 69.00 7.00 0.5922
s26 108469.71 20.00 7.00 8.00 0
s27 110667.84 22.00 28.00 7.00 0
s28 111660.57 2.00 42.00 4.00 0.2828
s29 110500.76 10.00 99.00 7.00 0.7303
s30 110918.29 6.00 0.00 2.00 0
s31 115520.49 20.00 5.00 7.00 0
s32 119535.68 11.00 20.00 0.00 0
s33 110183.27 23.00 78.00 3.00 0.5477
s34 109839.68 5.00 88.00 0.00 0
s35 110583.74 7.00 78.00 1.00 0.3162
s36 110186.17 4.00 54.00 8.00 0.4619
s37 125075.21 3.00 66.00 7.00 0.0413
s38 111151.44 22.00 36.00 3.00 0.1414
s39 109224.97 14.00 89.00 10.00 0.8641
s40 110556.28 14.00 23.00 0.00 0
s41 110575.67 4.00 82.00 4.00 0.4619
s42 107967.74 21.00 22.00 4.00 0
s43 111367.66 16.00 44.00 8.00 0.3300
s44 116276.03 9.00 75.00 8.00 0.3408
s45 118868.15 13.00 94.00 2.00 0.2152
the logistics of the proposals. Obviously, all the evaluation rules were
stated in the tender call.
For the fuzzification process the well-known piecewise linear and
sigmoidal membership functions were selected. In particular, for the
price criterion we chose a linear membership function that models
the fact that even negligible price variations are taken into account by
the tender committee (see Figure 1). Accordingly, the generic element
of the first column of the fuzzified decision matrix D’ was obtained by
defining the price membership function μ1 as follows:
d1max di1
d 'i1 1 (di1 ) , for i=1,…m, (5)
d1max d1min
di 2 d 2min
for di 2 [d 2min , d 2* ]
d 2* d 2min
d 'i 2 2 (di 2 ) , (6)
d 2max di 2
d for di 2 [d 2* , d 2max ]
d 2*
2max
for i=1,…m, with d 2min min di 2 and d 2max max di 2 ,
i 1,..., m i 1,..., m
d 2min 3d 2max
respectively (see Table 2). Moreover, we set d 2* ,
4
420 COSTANTINO, DOTOLI, FALAGARIO & PIA FANTI
TABLE 3
Top-Ranked Bidding Vendors for the Case Study
Position Supplier
1 s39
2 s10
3 s29
4 s12
5 s25
6 s14
7 s33
8 s7
9 s36
10 s41
(see Table 2), was assigned a zero overall performance index, due to
the too low free maintenance time offered by the vendor and the non-
compensatory nature of the technique.
The obtained results were analyzed together with the purchasing
manager responsible for the considered tender. Such an examination
showed that the FAHP supplier ranking fits with the synthetic, holistic
manager’s preferences resulting from his personal experience.
CONCLUSIONS
This paper contributes to the field of purchasing in the public
sector focusing on vendor assessment and selection in single-item
multiple sourcing exchanges. We have addressed the need for
supplier selection procedures in the public sector that are able to
deal with qualitative factors, as prescribed by the recent European
legislation, while maintaining the necessity for transparency typical of
public practices. We propose to enhance traditional vendor
evaluation and selection techniques in the public procurement sector
by employing fuzzy multiple criteria optimization and, in particular, the
well-known FAHP technique. The approach is tested by way of a case
study involving an Italian public administration, illustrating its
effectiveness for application to governmental purchasing.
Future work may consider additional qualitative factors related
either to the requested product/service or to the particular supplier,
USING FUZZY DECISION MAKING FOR SUPPLIER SELECTION IN PUBLIC PROCUREMENT 423
REFERENCES
Albino, V., Garavelli, A.C., & Gorgoglione, M. (1998). “Fuzzy Logic in
Vendor Rating: A Comparison between a Fuzzy Logic System and
a Neural Network.” Fuzzy Economic Review, 3: 25-48.
Amid, A., Ghodsypour, S.H., & O’Brien, C. (2006). “Fuzzy
Multiobjective Linear Model for Supplier Selection in a Supply
Chain.” International Journal of Production Economics, 104: 394-
407.
Araz, C., & Ozkarahan, I. (2007). “Supplier Evaluation and
Management System for Strategic Sourcing Based on a New
Multicriteria Sorting Procedure.” International Journal of
Production Economics, 106: 585-606.
Baily, P., Farmer, D., Jessop, D., & Jones, D. (2005). Purchasing,
Principles and Management (9th ed.). London, UK: Prentice Hall.
Bellmann, R., & Zadeh, L.A. (1970). “Decision Making in a Fuzzy
Environment.” Management Science, 17 (4): 141–164.
Bevilacqua, M., Ciarapica, F.E., & Giacchetta, G. (2006). “A Fuzzy-QFD
Approach to Supplier Selection.” Journal of Purchasing and
Supply Management, 12: 14-27.
Bouchon-Meunier, B., Dotoli, M., & Maione, B. (1996). “On the Choice
of Membership Functions in a Mamdani-Type Fuzzy Controller.” In
Proceedings of the First Online Workshop on Soft Computing (pp.
1-7), August 19-30. Nagoya, Japan.
Bruno, G., Esposito, E., Genovese, A., & Passaro, R. (2009). “A
Supplier Selection Model Based on a Multi-Criteria Analysis.” In
424 COSTANTINO, DOTOLI, FALAGARIO & PIA FANTI
Weber, C., Current, J.R., & Benton, W.C. (1991). “Vendor Selection
Criteria and Methods.” European Journal of Operational
Research, 50: 2-18.
Zadeh, L. A. (1965). “Fuzzy Sets.” Information and Control, 8: 338-
353.
Zimmermann, H.-J. (2001). Fuzzy Set Theory and Its Applications (4th
ed.). Boston, MA: Kluwer Academic Publishers.