Professional Documents
Culture Documents
A Two Phase Multi-Attribute Decision-Making Approach For New Product Introduction
A Two Phase Multi-Attribute Decision-Making Approach For New Product Introduction
A Two Phase Multi-Attribute Decision-Making Approach For New Product Introduction
www.elsevier.com/locate/ins
b,*
Istanbul Technical University, Department of Industrial Engineering, Macka 34367, Istanbul, Turkey
Galatasaray University, Department of Industrial Engineering, Ciragan Caddesi No. 36, Ortakoy 34357, Istanbul, Turkey
Received 6 September 2006; accepted 7 September 2006
Abstract
This study aims at improving the quality and eectiveness of decision-making in new product introduction. New product development has long been recognized as one of the corporate core functions to be competitive on an increasingly competitive global market. However, developing new products is a process involving risk and uncertainty. In order to solve this
stochastic problem, companies need to evaluate their new product initiatives carefully and make accurate decisions. For
this reason, a systematic decision process for selecting more rational new product ideas is proposed. Basically, two stages of
decision-making are described: the identication of nondominated new product candidates and the selection of the best
new product idea. These stages are composed of an integrated approach based on a fuzzy heuristic multi-attribute utility
method and a hierarchical fuzzy TOPSIS method. Finally, an application is given to demonstrate the potential of the
methodology.
2006 Published by Elsevier Inc.
Keywords: New product idea selection; Fuzzy sets; Heuristics; Multi-attribute utility function; TOPSIS method
1. Introduction
In an increasingly competitive global market, companies must be better at developing new products. New
product development (NPD) has long been recognized as one of the corporate core functions. Particularly for
the companies with short product life cycles, it is important to develop new products and new product platforms that fulll reasonable demands on quality, performance, and cost quickly and safely.
NPD which translates an idea into a tangible physical asset is structured around well-dened phases.
Each phase encloses many decision points, where management decides about the future of the project
[26]. One of the most critical decisions when managing NPD projects is the new product idea selection
[1,4]. Several researchers conclude that it is dicult for managers to end the NPD projects once they are
Corresponding author. Tel.: +90 212 227 4480; fax: +90 212 259 5557.
E-mail address: gbuyukozkan@gsu.edu.tr (G. Buyukozkan).
1568
begun [12,35]. This is the main motivation of this study, which focuses on making an ecient new product
idea selection.
Similar to all decision problems, NPD decisions contain considerable amount of uncertainty causing elements, which confuse the decision-maker to reach the targeted performance [2,33]. Uncertainty arises from
both internal and external multiple sources including technical, management, and commercial issues. Thus,
it is critical to use a structured approach that can minimize the risks of NPD projects. To help consumers
and decision-makers easily express their judgments, the linguistic variables should be used to evaluate the
importance of customer needs and ratings of new product alternatives. The fuzzy set theory is a useful tool
for this aim. In this article, we propose an integrated approach with two phases based on a fuzzy heuristic
multi-attribute utility method and the hierarchical fuzzy TOPSIS method to make more rational selection
decisions. The rst phase of our approach evaluates all the alternatives to eliminate the alternatives clearly
dominated by the others. The second phase involves a more detailed analysis to select the best one among
the remaining nondominated alternatives. We also present an industrial application to demonstrate the potential of this integrated approach.
The rest of the paper is organized as follows. The next section presents an overview of the decision-making
techniques used in a NPD process. The details of the proposed integrated approach are given in Section 3. An
application of the approach is described in Section 4 through a case study. Finally, the last section contains
some concluding remarks and possible perspectives.
2. An overview for new product decision methods
NPD has a vast working area and it addresses dierent strategic, tactic, and operational managerial levels
in the organization. Although dierent organizations can make dierent choices and may use dierent methods, all of them make decisions about a collection of issues such as the product concept, architecture, conguration, procurement, distribution arrangements, and project schedule, etc. Consequently, NPD can be
dened as a process including many generic decision points, where each of them must be evaluated, selected,
and prioritized. While considering the decision points in the whole NPD process, numerous decision tools and
techniques have been developed to assist managers in making better screening decisions in an uncertain environment [10,11,1315,19,22,23,28,36,38,39]. Some of them may be classied in that way: Probabilistic models
[37], Options pricing theory [18], Scoring models and checklists [20,32], Behavioral approaches [37], Analytical
hierarchy process [43], Sensitivity analysis [34], and Fuzzy logic [19]. These techniques can be used exclusively
or in a hybrid way. In this study, we propose a two phase integrated decision-making approach based on fuzzy
heuristic multi-attribute utility and hierarchical fuzzy TOPSIS methods as given in Fig. 1. The decision-makers
are actively involved in the decision process of the proposed approach. For example, heuristic information is
obtained through a question and answer system, where a dialogue between the decision-makers and the analysts takes place, and the decision rules are constructed through serious discussions between the decision-makers and the analysts. In the following, this two phase approach is presented.
3. A two phase approach for selection among new product ideas
3.1. Heuristic multi-attribute utility function approach
One of the basic principles of the classical economic theory is that decision-makers behave as prot maximizers. According to this principle, the problem of NPD could be adequately modeled by the maximization of
single-objective models. Real-life observations refute this simplication. Expected utility theory (EUT) was a
rst step in the direction of broadening the prot maximizer assumption and including higher moments of the
expected prot. However, EUT has been criticized for limiting its application to a single attribute: the pay-o
(or wealth). Many authors have shown the complexity of the NPD decision-making process through empirical
studies that have demonstrated that they consider more than one attribute in their utility functions [3,4,33]. All
the related studies suggest that NPD decision-making processes are driven by various criteria, usually conicting ones, related to their economic, social, and cultural environment situation, in addition to the expected
prot.
1569
INITIALIZATION PHASE
1. Identify the interest groups of people in the decision environment
PHASE I
4. Interact with decision makers to identify their heuristics and according
to them, construct heuristic decision rules for each group.
5. List the selected most appropriate alternatives and measure along the
attributes.
PHASE II
6. Identify the weights of main and sub evaluation criteria with respect to
goal and main criteria respectively.
9. Rank the alternatives from the best to the worst and select the best new
product idea for the company.
Recognizing the convenience of including several objectives to simulate evaluator or decision-maker behavior, we resort to Multi-attribute utility theory (MAUT), an approach largely developed by Keeney and Raia
[25], in order to overcome the limitations of the single-attribute utility function. The aim of MAUT is to
reduce a decision problem with multiple criteria to a cardinal function that ranks alternatives according to
a single criterion. Thus, the utilities of n attributes from dierent alternatives are captured in a quantitative
way via a utility function represented mathematically as U = U(r1, r2, . . . , rn), where U is the Multi-attribute
utility function (MAUF) and rj is the attribute j. The level of achievement of each attribute can usually be
expressed mathematically as a function of the decision variables. Thus, decisions under MAUT are made
by maximizing U and responding to the set of objectives that are simultaneously aimed at by the decisionmaker.
1570
A heuristic method is an algorithm that gives only an approximate solution to a given problem. Sometimes
we are not able to formally prove that this solution actually solves the problem, but heuristic methods are
commonly used because they are much faster than exact algorithms. In addition, this is a software-based strategy, which is therefore relatively cheap and available to any researcher. Efstathiou and Rajkovic [16] and
Efstathiou [17] argued that the MAUF could not be practically obtained by the combination of single-attribute utility functions because of the dependency among attributes. Therefore a heuristic approach is needed to
dene the MAUF [6]. Since decision data may be numerically and/or linguistically expressed, the fuzzy set
theory must be incorporated in this heuristic approach. The utility function is represented then in the
IF . . . THEN . . . decision rule format.
3.2. Hierarchical fuzzy TOPSIS methodology
3.2.1. Fuzzy TOPSIS
TOPSIS (Technique for order preference by similarity to ideal solution) views a multi-attribute decisionmaking problem with m alternatives as a geometric system with m points in the n-dimensional space. It
was developed by Hwang and Yoon [21]. The method is based on the concept that the chosen alternative
should have the shortest distance from the positive-ideal solution and the longest distance from the negative-ideal solution. TOPSIS denes an index called similarity (or relative closeness) to the positive-ideal solution and the remoteness from the negative-ideal solution. Then the method chooses an alternative with the
maximum similarity to the ideal solutions [41].
In the last 15 years, some fuzzy TOPSIS methods were developed in the literature. Table 1 gives the comparison of these fuzzy TOPSIS methods. The comparison includes the computational dierences among the
methods.
This study is based on the Chen and Hwangs [6] fuzzy TOPSIS method since the other fuzzy TOPSIS
methods are derived from this method with minor dierences. In the following, the steps of fuzzy TOPSIS
developed by Chen and Hwang [6] are given. First, a decision matrix, D, of m n dimension is dened as
in Eq. (1).
A1
X1 Xj
x11 x1j
6
6 ..
6.
6
6
D Ai 6
6 xi1
6
.. 6 .
.
. 6
4.
Am
..
.
..
.
xm1
xij
..
.
xmj
Xn
3
x1n
7
.. 7
. 7
7
7
xin 7
7
7
.. 7
. 7
5
xmn
where xij " i, j may be crisp or fuzzy. If xij is fuzzy, it is represented by a trapezoidal number as xij = (aij, bij,
cij, dij) shown in Fig. 2. The fuzzy weights can be described by Eq. (2).
~ j aj ; bj ; vj ; dj
w
1571
Table 1
Comparison of fuzzy TOPSIS methods
Source
Attribute
weights
Type of fuzzy
numbers
Ranking method
Normalization
method
Chen and
Hwang [6]
Liang [29]
Fuzzy
numbers
Fuzzy
numbers
Fuzzy
numbers
Fuzzy
numbers
Crisp values
Trapezoidal
Trapezoidal
Linear
normalization
Manhattan distance
Triangular
Triangular
Triangular
Triangular
Chen [5]
Chu [8]
Tsaur et al.
[40]
Chu and Lin
[9]
Zhang and Lu
[44]
Triangular
Fuzzy
numbers
Crisp values
(x )
1.0
0.9
0.8
0.7
0.6
0.5
0.4
0.3
0.2
0.1
0
wj
xij
j
aij
bij
Linear
normalization
Modied
Manhattan distance
Vector
normalization
Linear
normalization
Manhattan distance
j
cij
d ij
2 X1
r11
6.
6 ..
6
6
6 ri1
6
6.
6.
4.
Am
rm1
Xj
r1j
..
.
rij
..
.
rmj
Xn 3
r1n
.. 7
. 7
7
7
rin 7
7
.. 7
7
. 5
rmn
When xij is crisp, its corresponding rij must be crisp; when xij is fuzzy, its corresponding rij must be
fuzzy. Eq. (3) is then replaced by the following fuzzy operations. Let xij aij ; bij ; cij ; d ij ; x
j
a
j ; bj ; cj ; d j and xj aj ; bj ; cj ; d j , we have
8
a
b
c
d
>
< xij xj dijj ; cij ; bijj ; aij
j
j
rij
5
>
: x xij ai ; bi ; ci ; d i
j
d ij cij bij aij
Step 2. Obtain the weighted normalized decision matrix. This matrix is obtained using
vij rij wj
8j ; j
1572
When both rij and wij are crisp, vij is crisp; while when either rij or wij (or both) are fuzzy, Eq. (6) may
be replaced by the following fuzzy operations:
!
aij bij
cij d ij
vij rij wj
aj ; bj ; vj ; dj
7
d j
cj
bj
aj
ai
b
c
d
i
i
i
aj ; bj ; vj ; dj
8
vij rij wj
d ij
cij
bij
aij
Eq. (7) is used when the jth attribute is a benet attribute. Eq. (8) is used when the jth attribute is a
cost attribute. The result of Eqs. (7) and (8) can be summarized as in Eq. (9).
2 X1
A1 v11
.. 6
6.
. 6 ..
6
v Ai 6
6 vi1
.. 6
6.
. 4 ..
Am vm1
Xj
v1j
..
.
vij
..
.
Xn 3
v1n
.. 7
7
. 7
7
vin 7
7
.. 7
7
. 5
vmj
vmn
Step 3. Obtain the positive ideal solution (PIS), A*, and the negative ideal solution (NIS). PIS and NIS are
dened as
A v1 ; . . . ; vn ;
10
A v
1 ; . . . ; vn ;
11
where vj maxi vij and v
j mini vij . For crisp data, vj and vj are obtained straightforwardly. In case
of fuzzy data, vj and vj may be obtained through some ranking procedures. Chen and Hwang [6] use
Lee and Lis ranking method [27] for comparison of fuzzy numbers. The vj and v
j are the fuzzy numbers with the largest generalized mean and the smallest generalized mean, respectively. The generalized
mean for fuzzy number vij 8j is dened as
Mvij
12
For each column j, we nd a vijwhose greatest mean is vj and lowest mean is v
j .
Step 4. Obtain the separation measures S i and S
i . In the classical case, separation measures are dened as
n
X
Dij ; i 1; . . . ; m
13
S i
j1
and,
S
i
n
X
D
ij ;
i 1; . . . ; m
14
j1
15
D
ij jvij vj j
16
The computation is straight forward. For fuzzy data, the dierence between two fuzzy numbers lvij x
and lvj x (based on Zadehs study [42]) is explained as given in Eq. (17).
^
8i; j
17
(x)
vj*
vij
1.
1573
Lij
x
Fig. 3. The derivation of Lij.
where Lij is the highest degree of similarity of vij and vj . The value of Lij is depicted in Fig. 3. Similarly,
the dierence between lvij x and lvj x is dened as
^
D
xcg 1 Lij
ij 1 fsupblvij x lv
j
8i; j
18
19
GOAL
MA1
SA11
SA12
...
MA2
SA1r1
SA21
SA22
MAP
...
SA2r2
...
SApl
MAn
...
SAn1
SAn2
...
SAnr n
1574
eI MA
MA1
MA2 2Goal3
~1
w
..
6
.
~2 7
6w
7
6 7
MAp 4 w
~p 5
..
~n
w
.
20
MAn
~ p is the arithmetic mean of the weights assigned by the respondents and is calculated by Eq. (21):
where w
Ps
~
qpi
~ p i1 ; p 1; 2; . . . ; n
21
w
s
where ~
qpi denotes the fuzzy evaluation score of pth main attribute with respect to goal assessed by the ith
respondent. The second matrix eI SA represents the weights of the sub-attributes with respect to the main attributes. The weights vector obtained from eI MA are written above this eI SA as illustrated in Eq. (22).
~1
w
SA11
SA12
..
.
SA1r1
SA21
SA22
..
.
eI SA SA2r2
..
.
SApl
..
.
SAn1
SAn2
..
.
SAnrn
~2
w
~p
w
0
~n
w
MA3
n
0
7
0 7
7
7
..
7
7
.
7
7
0 7
7
7
0 7
7
7
0 7
7
7
..
7
.
7
7
0 7
7
7
7
..
7
.
7
7
0 7
7
7
7
0 7
7
7
~ n1 7
w
7
7
~ n2 7
w
7
7
7
..
7
.
5
~ nrn
w
22
~ pl is the arithmetic mean of the weights assigned by the respondents and it is calculated by Eq. (23).
where w
Ps
~
qpli
~ pl i1
23
w
s
where ~
qpli is the weight of lth sub-attribute with respect to pth main attribute assessed by the ith respondent.
1575
The third matrix eI A is formed by the scores of the alternatives with respect to the sub-attributes. The
weights vector obtained from eI SA are written above this eI A as in Eq. (24).
~ 11
w
~ 12
w
~ 1r1
... w
SA
2 11 SA12 . . . SA1r1
~c111 ~c112 . . . ~c11r1
6
A2 6 ~c211 ~c212 . . . ~c21r1
6
.. 6
..
..
..
. 6
.
.
.
6
eI A
6
Aq 6 ~cq11 ~cq12 . . . ~cq1r1
6
.. 6
..
..
. 6
.
.
4
Ak ~ck11 ~ck12 . . . ~ck1r1
A1
...
~ pl
w
. . . SApl
. . . ~c1pl
. . . ~c2pl
..
.
. . . ~cqpl
..
.
. . . ~ckpl
...
~ nrn
w
. . . SAnr3n
. . . ~c1nrn
7
. . . ~c2nrn 7
7
7
..
7
.
7
7
. . . ~cqnrn 7
7
7
..
7
.
5
. . . ~cknrn
24
where
e pl
W
n
X
25
~ pw
~ pj
w
j1
Since wpj = 0 for j 5 l, we can use Eq. (26) instead of Eq. (25)
e pl w
~ pw
~ pl
W
26
In eI A ; ~cqpl is the arithmetic mean of the scores assigned by the respondents and it is calculated by Eq. (27)
Ps
~
qqpli
~cqpl i1
27
s
where ~
qqpli is the fuzzy evaluation score of qth alternative with respect to lth sub-attribute under pth main attribute assessed by ith respondent.
After obtaining ~cqpl s, the hierarchical structure is ready to be included to the fuzzy TOPSIS algorithm
described in Section 3.2.1.
Table 2 will be used to determine the importance degree of each main attribute with respect to the goal and
each sub-attribute with respect to the main attributes. The linguistic terms represented by triangular fuzzy
numbers for scoring the alternatives are given in Table 3. Among the types of fuzzy numbers, the choice of
triangular fuzzy numbers is made for the sake of simplicity and understandability. The other types may
increase the computational complexity without substantially aecting the signicance of the results.
Table 2
The importance degrees
Very low
Low
Medium
High
Very high
(0, 0, 0.2)
(0, 0.2, 0.4)
(0.3, 0.5, 0.7)
(0.6, 0.8, 1)
(0.8, 1, 1)
Table 3
The scores
Very poor
Poor
Fair
Good
Very good
(0, 0, 20)
(0, 20, 40)
(30, 50, 70)
(60, 80, 100)
(80, 100, 100)
1576
Benefits
Strategic
Impact
Profitability
Strategic value
Efficiency
Business impact
Risks
Systematic
risks
Unsystematic
risks
Financial
Managerial
Technical
Personnel
1577
(x)
VL
VLL
ML
MH
HVH
60
70
80
VH
1.0
10
20
30
40
50
90
100
Fig. 6. The membership function for the evaluation aspect risk and strategic impact.
(x )
VL VLL
ML
150
200
250
MH
HVH
300
350
400
VH
1.0
50
100
450 500
x ( $1,000)
After identifying all decision rules, we listed all alternatives and evaluated them according to the determined
rules. Then we obtained the utility values of each alternative as given in Table 4. Five alternatives (NPIs 1, 4, 9,
11 and 14), which have the highest utility values, were identied for a detailed analysis.
Table 4
The linguistic evaluation of the alternatives with respect to each criterion
Alternatives
Benets
Strategic impact
Risks
Utility
NPI-1
NPI-2
NPI-3
NPI-4
NPI-5
NPI-6
NPI-7
NPI-8
NPI-9
NPI-10
NPI-11
NPI-12
NPI-13
NPI-14
Very high
Very low to low
Mediumgood
High
High
Mediumhigh
Medium
Very high
High
High
Very high
Medium
Low
High to very high
Low
Medium
Very low to low
Low
Mediumlow
Low
Mediumlow
High
Very low to low
Low
Mediumlow
Medium
Mediumhigh
Low
Very good
Mediumpoor
Good
Very good
Good
Mediumgood
Medium
Good
Very good
Good
Very good
Mediumgood
Mediumpoor
Very good
1578
29
Dij and D
ij are calculated by Eqs. (30) and (31), respectively.
8
cij a
>
>
< 1 b c a b for bij < b
ij
ij
8i; j
Dij
c aij
>
>
:1
for
b
<
b
ij
bij c aij b
8
c aij
>
>
< 1 b c a b for b < bij
ij
ij
Dij
8i; j
cij a
>
>
for
b
<
b
:1
ij
b cij a bij
30
31
where vj a ; b ; c and v
j a ; b ; c are the fuzzy numbers with the largest generalized mean and the
smallest generalized mean, respectively.
Then, the steps of the hierarchical fuzzy TOPSIS algorithm are executed. The model considered in the study
has three main attributes, six sub-attributes, four sub-sub-attributes and ve alternatives. The evaluations
from all nine respondents were received and eI MA , eI SA and eI A were obtained as in Tables 58.
Table 5
eI MA
Goal
Benets
Strategic impact
Risks
Table 6
eI SA
Protability
Eciency
Strategic value
Business impact
Systematic risks
Unsystematic risks
Benets
Strategic impact
Risks
1579
Table 7
eI SSA
Financial
Technical
Managerial
Personnel
Systematic risks
Unsystematic risks
Table 8
eI A
Prociency
Eciency
Strategic impact
Business value
NPI-1
NPI-4
NPI-9
NPI-11
NPI-14
NPI-1
NPI-4
NPI-9
NPI-11
NPI-14
Financial risks
(51, 64, 78)
(47, 60, 73)
(32, 48, 66)
(42, 56, 69)
(55, 69, 75)
Technical risks
(48, 66, 81)
(47, 63, 73)
(24, 31, 47)
(33, 42, 56)
(49, 62, 73)
Managerial risks
(51, 64, 73)
(69, 87, 91)
(32, 48, 66)
(49, 67, 75)
(49, 62, 73)
Personnel risks
(43, 61, 79)
(52, 74, 88)
(32, 48, 66)
(39, 54, 72)
(42, 60, 78)
Table 9
Distances from the ideal solution
NPI-1
NPI-4
NPI-9
NPI-11
NPI-14
S i
S
i
Ci
Normalized Ci
0.278
0.298
1.213
0.691
0.414
0.952
0.913
0.024
0.546
0.886
0.774
0.754
0.020
0.441
0.681
0.290
0.282
0.007
0.165
0.255
Table 9 shows the distances from the ideal solution for each NPI and the normalized values making
the results easy to interpret. The results in Table 9 indicate that NPI-1 achieves the highest score whereas
NPI-9 has the lowest.
4.4. Results
From a set of 14 NPIs, rst a rough evaluation is made with heuristic MAUF approach using the rules
dened by decision-makers. The rst phase determined that NPIs 1, 4, 9, 11, and 14 were to be considered
in the second phase for a detailed evaluation by the fuzzy hierarchical TOPSIS approach. The reduced set
of alternatives selected with respect to the evaluations is analyzed by the hierarchy developed in the initialization phase. A ranking among the reduced set of alternatives is the result of the second phase. The obtained
results indicate that NPI-1, NPI-4, and NPI-14 are the rst NPIs to invest. Although NPI-9 is selected in the
rst phase, it is not eligible to invest it because of its relatively low score.
4.5. Sensitivity analysis
To analyze the attitudes of the alternatives under dierent weights of main attributes, a sensitivity analysis
is made. The results of the sensitivity analysis are given in Table 10 and the graphical representation of these
results is illustrated in Fig. 8. Four states in total are examined: One of the main attributes has the highest
1580
Table 10
Sensitivity analysis
B
SI
Normalized Ci
States
NPI-1
NPI-4
NPI-9
NPI-11
NPI-14
1
2
3
4
0.233
0.412
0.236
0.278
0.109
0.156
0.334
0.262
0.091
0.021
0.045
0.049
0.266
0.154
0.139
0.169
0.300
0.257
0.246
0.243
Normalized Ci
0. 500
0. 400
0. 300
0. 200
0. 100
0. 000
4
3
NPI-1
NPI-4
NPI-9
NPI-11
es
at
St
NPI-14
possible weight whereas the other two have the minimum (this creates three states). The fourth state is considered for the equal mid-value weights. For each state, normalized relative closeness to ideals (Ci) are
computed.
It is clear that not only the importance of sub and sub-sub-attributes but also the importance of main attributes are very inuential to the selection process. The sensitivity application shows us prioritization of NPI-1,
4, and 14 are eected by decision-makers perceptions about main attributes. In State 1 where the benet
aspect has the largest weight, NPI-11 performs close to NPI-14.
5. Conclusion
In todays fast and dynamic markets for innovative products, the success of a product highly depends on
the eciency and eectiveness of the NPD process. A particularly important key to the adequacy of a NPD
process is the way in which it is capable of handling uncertainty. On the other hand, developing new products
is a risky process involving uncertainty. In order to reduce these risks and uncertainties, companies need to
evaluate their new product initiatives carefully and make accurate decisions.
In this paper, an integrated approach based on fuzzy heuristic MAUF and hierarchical fuzzy TOPSIS
method is proposed to improve the quality and eectiveness of decision-making in new product introduction.
The approach is based on the premise that the selection among NPIs should be viewed as a product of benets,
strategic impact, and risks. The rst phase of the evaluation consists of judgments of decision-makers with
respect to these three main attributes, whereas the second phase considers a detailed hierarchy of attributes
and alternatives.
It is clear that the selection among NPIs is a dicult and sensitive issue which has quantitative and qualitative aspects, complexity, and imprecision. The developed two phase multi-attribute decision-making
1581
approach seems to be usable for the solution of this problem. For further research, the other single level multiattribute methods like outranking methods and multi-attribute utility theory can be developed to compare
with the results of fuzzy hierarchical TOPSIS.
References
[1] G. Buyukozkan, O. Feyzioglu, A new approach based on soft computing to accelerate new product introduction, Computers in
Industry 54 (2004) 151167.
[2] G. Buyukozkan, O. Feyzioglu, A fuzzy-logic-based decision-making approach for new product development, International Journal of
Production Economics 90 (2004) 2745.
[3] G. Buyukozkan, O. Feyzioglu, Accelerating the new product introduction with intelligent data mining, in: D. Ruan, G. Chen, E.E.
Kerre, G. Wets (Eds.), Intelligent Data Mining Techniques and Applications, Springer, 2005, pp. 375394.
[4] P. Carbonell-Foulquie, J.L. Munuera-Aleman, A.I. Rodrguez-Escudero, Criteria employed for go/no-go decisions when developing
successful highly innovative products, Industrial Marketing Management 33 (2004) 307316.
[5] T.-C. Chen, Extensions of the TOPSIS for group decision-making under fuzzy environment, Fuzzy Sets and Systems 114 (2000) 19.
[6] S.J. Chen, C.L. Hwang, Fuzzy Multiple Attribute Decision Making Methods and Applications, Springer-Verlag, Berlin, 1992.
[7] S.H. Chen, Ranking fuzzy numbers with maximizing set and minimizing set, Fuzzy Sets and Systems 17 (1985) 113129.
[8] T.-C. Chu, Facility location selection using fuzzy TOPSIS under group decisions, International Journal of Uncertainty, Fuzziness and
Knowledge-Based Systems 10 (2002) 687701.
[9] T.-C. Chu, Y.-C. Lin, A fuzzy TOPSIS method for robot selection, International Journal of Advanced Manufacturing Technology 21
(2003) 284290.
[10] M.A. Cohen, J. Eliashberg, T.-H. Ho, New product development: the performance and time-to-market tradeo, Journal of Product
Innovation Management 14 (1997) 6566.
[11] S. Coldrick, P. Longhurst, P. Ivey, J. Hannis, An R&D options selection model for investment decisions, Technovation 25 (2005) 185
193.
[12] R.G. Cooper, Perspective: third generation new product processes, Journal of Product Innovation Management 11 (1994) 314.
[13] R.G. Cooper, Winning at New Products: Accelerating the Process from Idea to Launch, third ed., Pereus Publishing, New York,
2001.
[14] T. Davila, An empirical study on the drivers of management control systems design in new product development, Accounting,
Organizations and Society 25 (2000) 383409.
[15] R.N. Doctor, D.P. Newton, A. Pearson, Managing uncertainty in research and development, Technovation 21 (2001) 7990.
[16] J. Efstathiou, V. Rajkovic, Multi-attribute decision-making using a fuzzy heuristic approach, IEEE Transaction on Systems, Man,
Cybernetics 9 (1979) 326333.
[17] J. Efstathiou, The incorporation of objective and subjective aspects into the assessment of information systems, in: Lucas, Land,
Lincoln, Supper (Eds.), The Information Systems Environment, North-Holland, 1980, pp. 187197.
[18] T. Faulkner, Applying options thinking to R&D valuation, Research and Technology Management 39 (1996) 5057.
[19] A.C. Garavelli, M. Gorgoglione, B. Scozzi, Fuzzy logic to improve the robustness of decision support systems under uncertainty,
Computers and Industrial Engineering 37 (1999) 477480.
[20] D.L. Hall, A. Naudia, An interactive approach for selecting R&D project, IEEE Transactions on Engineering Management 37 (1990)
126133.
[21] C.L. Hwang, K. Yoon, Multiple Attribute Decision Making Methods and Applications, Springer-Verlag, New York, 1981.
[22] G. Infanger, Planning Under Uncertainty, International Thomson Publishing, MA, 1994.
[23] P. Jovanovic, Application of sensitivity analysis in investment project evaluation under uncertainty and risk, International Journal of
Project Management 17 (1999) 217222.
[24] A. Kaufmann, M.M. Gupta, Fuzzy Mathematical Models in Engineering and Management Science, North Holland, 1988.
[25] R.L. Keeney, H. Raia, Decisions with Multiple Objectives: Preferences and Value Trade Os, John Wiley & Sons, New York, 1976.
[26] V. Krishnan, K.T. Ulrich, Product development decisions: a review of the literature, Management Science 47 (2001) 121.
[27] E.S. Lee, R.L. Li, Comparison of fuzzy numbers based on the probability measure of fuzzy events, Computer and Mathematics with
Applications 15 (1988) 887896.
[28] S. Li, The development of a hybrid intelligent system for developing marketing strategy, Decision Support Systems 27 (2000) 395409.
[29] G.-S. Liang, Fuzzy MCDM based on ideal and anti-ideal concepts, European Journal of Operational Research 112 (1999) 682691.
[30] T.S. Liou, M.J.J. Wang, Ranking fuzzy numbers with integral value, Fuzzy Sets and Systems 50 (1992) 247.
[31] H. Markowitz, Portfolio selection, The Journal of Finance 7 (1952) 7791.
[32] M.M. Montoya-Weiss, R.J. Calantone, Determinants of new product performance: a review and meta analysis, Journal of Product
Innovation Management 11 (1994) 397417.
zer, Factors which inuence decision making in new product evaluation, European Journal of Operational Research 163 (2005)
[33] M. O
784801.
[34] G.S. Parnell, J.A. Jackson, R.C. Burk, L.J. Lehmkuhl, J.A. Engelbrecht, R&D concept decision analysis: using alternate futures for
sensitivity analysis, Journal of Multi-Criteria Decision Analysis 8 (1999) 119127.
[35] J.B. Schmidt, R.J. Calantone, Are really new product development projects harder to shut down? Journal of Product Innovation
Management 15 (1998) 111123.
1582
[36] M.F. Shipley, A. de Korvin, O. Khursheed, A fuzzy logic-based decision model to satisfy goals for successful product/service
introduction, European Journal of Operational Research 135 (2001) 209219.
[37] W.E. Souder, T. Mandakovic, R&D project selection models, Research Management 29 (1986) 3642.
[38] G.L. Trittle, E.F.V. Scriven, A.R. Fusfeld, Resolving uncertainty in R&D portfolios, Research and Technology Management March
April (2000) 4755.
[39] H.-C. Tsai, S.-W. Hsiao, Evaluation of alternatives for product customization using fuzzy logic, Information Sciences 158 (2004)
233262.
[40] S.-H. Tsaur, T.-Y. Chang, C.-H. Yen, The evaluation of airline service quality by fuzzy MCDM, Tourism Management 23 (2002)
107115.
[41] K.P. Yoon, C.L. Hwang, Multiple Attribute Decision Making: An Introduction, Sage Publications, Thousand Oaks, 1995.
[42] L.A. Zadeh, Fuzzy sets, Information and Control 8 (1965) 338353.
[43] F. Zahedi, The analytic hierarchy processa survey of the method and its applications, Interfaces 16 (1996) 108.
[44] G. Zhang, J. Lu, An integrated group decision-making method dealing with fuzzy preferences for alternatives and individual
judgments for selection criteria, Group Decision and Negotiation 12 (2003) 501515.
[45] R. Zhao, R. Govind, Algebraic characteristics of extended fuzzy numbers, Information Sciences 54 (1991) 103130.
Further reading
[46] R.J. Calantone, C.A. Di Benedetto, J.B. Schmidt, Using the analytic hierarchy process in new product screening, Journal of Product
Innovation Management 16 (1999) 6576.