Xem mẫu
- MODELLING IMPORTANCE PREFERENCES IN CUSTOMER
SATISFACTION SURVEYS
E. Grigoroudis(1), Y.Politis(1), O. Spyridaki(1) and Y. Siskos(2),
(1)
Technical University of Crete
Decision Support Systems Laboratory
University Campus, 73100 Chania, Greece
Tel. +30-8210-37346 / Fax +30-8210-64824
Email: vangelis@ergasya.tuc.gr
(2)
University of Piraeus
Department of Informatics
Karaoli Dimitriou 80, 18534 Piraeus, Greece
Tel. +30-10-4142260 / Fax +30-10-4142264
Email: ysiskos@unipi.gr
ABSTRACT
Customer satisfaction measurement, through MUSA model, provides the analysts with the
highest and lowest performance indicators, pointing out the leverage opportunities and the
weaknesses of the company. An extension of the MUSA methodology for modelling customer
importance preferences for service characteristics is presented in this paper. Several approaches
in the context of multiobjective linear programming are examined, which give the ability to
compare derived and modelled weights of the satisfaction dimensions and to introduce the
principles of Kano’s model to MUSA methodology. Finally, the results of an application of the
MUSA extension to an educational organization are presented in this paper.
Key words: Customer satisfaction analysis, MUSA method, Satisfaction importance modelling,
Kano’s model.
1. INTRODUCTION
To reinforce customer orientation on a day-to-day basis, a growing number of companies
choose customer satisfaction as their main performance indicator. However, customer
satisfaction must be translated into a number of measurable parameters directly linked to several
aspects of a company’s products/services or else it will remain an abstract and intangible notion.
Measurement will provide the analysts with the highest and lowest performance indicators,
pointing out the leverage opportunities and the weaknesses of the company.
It often happens that derived importance by a preference disaggregation model differs from the
stated importance. By the term stated importance we refer to the importance that is given to
each criterion by the customers. It is not unreasonable to say that customers tend to rate every
criterion as important, when asked freely (Naumann and Giel, 1995).
The aim of this paper is to present an extension of the MUSA methodology that helps modelling
customer importance preferences for service characteristics. This approach gives the ability to
compare derived and modelled weights of the satisfaction dimensions and to extrapolate
valuable results. The results of an application of the MUSA extension to an educational
organization, give an example of the differentiation between derived and stated importance.
This paper is organised in 4 sections. Section 2 presents briefly the mathematical background of
importance preferences modeling. Here are presented the basic principles of Kano’s model and
1
- MUSA method, as well as a summary description of customers’ preferences importance
modelling with MUSA. The main results of the application for the customers of an educational
organization are presented in section 3. Section 4 summarizes some concluding remarks, along
with the basic advantages of the MUSA extension.
2. DIFFERENT METHODOLOGICAL APPROACHES FOR CUSTOMER
SATISFACTION
2.1. Kano’s model for customer satisfaction
In many cases customer satisfaction has been seen mostly as a one-dimensional construction –
the higher the perceived product quality, the higher the customer’s satisfaction and vice versa.
But fulfilling the individual product/service requirements to a great extent does not necessarily
imply a high level customer satisfaction. It is also the type of requirement which defines the
perceived product/service quality and thus customer satisfaction. A characteristic example of
this situation is the assessment of customer satisfaction for a pen point (Vavra, 1997). If the
flow of the ink is not sufficient (or it is more than needed), customers will state a high level of
dissatisfaction. On the other hand, if the flow of the ink is sufficient, it is possible that the
customers will not state a high level of satisfaction, considering that the particular attribute is a
necessary and expected feature of the product.
In his model (see figure 1), Kano (1984) distinguishes between three types of product/service
requirement which influence customer satisfaction in different ways when met. Based on the
Kano model, it can be recognized that customer satisfaction is more than one-level issue as
traditionally viewed. It may not be enough to merely satisfy customers by meeting their basic
and spoken requirements under current highly competitive environments. One main reason is
that nowadays there are so many similar products for customers to choose from in the
marketplace. The three types of product/service requirements in the Kano model are (Kano
1984):
Must-be requirements
The must be requirements are basic criteria of a product/service. If these requirements are not
fulfilled, the customer will be extremely dissatisfied. On the other hand, as the customer takes
these requirements for granted, their fulfillment will not increase his satisfaction. Fulfilling the
must-be requirements will only lead to a state of “not dissatisfied”. The customer regards the
must-be requirements as prerequisites, he takes them for granted and therefore does not
explicitly demand them. Must-be requirements are in any case a decisive competitive factor, and
if they are not fulfilled, the customer will not be interested in the product/service at all.
One dimensional requirements
With regard to these requirements, customer satisfaction is proportional to the level of
fulfillment – the higher the level of fulfillment, the higher the customer’s satisfaction and vice
versa. One-dimensional requirements are usually explicitly demanded by the customer.
Attractive requirements
These requirements are the product/service criteria which have the greatest influence on how
satisfied a customer will be with a given product/service. Attractive requirements are neither
explicitly expressed nor expected by the customer. Fulfilling these requirements leads to more
than proportional satisfaction. If they are not met, however, there is no felling of dissatisfaction.
It must be noticed that the specific classification of customer requirements to one of the above
categories is dynamic and affected from the competitiveness of the market. Thereby, an
attractive attribute of a product/service may in a short time become one-dimensional or even
expected attribute.
2
- Customer satisfied
Attractive requirements
- not expressed
- customer-tailored One dimensional
- cause delight requirements
- articulated
- specified
- measurable
- technical
Requirement Requirement
not fulfilled fulfilled
Must-be requirements
- implied
- self-evident
- not expressed
- obvious
Customer dissatisfied
Source: Berger et al., 1993
Figure 1: Kano’s model of customer satisfaction
The advantages of classifying customer requirements by means of the Kano method are very
clear (Matzler et al., 1996, Matzler and Hinterhuber, 1998):
• Product requirements are better understood: the product/service criteria which have the
greatest influence on the customer’s satisfaction can be identified. Classifying
product/service requirements into must-be, one dimensional and attractive dimensions can
be used to focus on.
• Priorities for product development. It is, for example, not very useful to invest in improving
must-be requirements which are already at a satisfactory level but better to improve one-
dimensional or attractive requirements as they have a greater influence on perceived
product/service quality and consequently on the customer’s level of satisfaction.
• Kano’s method provides valuable help in trade-off situations in the product development
stage. If two product requirements cannot be met simultaneously due to technical or
financial reasons, the criterion which has the greatest influence on customer satisfaction can
be identified.
• Must-be, one-dimensional and attractive requirements differ, as a rule, in the utility
expectations of different customer segments. From this starting point, customer-tailored
solutions for special problems can be elaborated which guarantee an optimal level of
satisfaction in the different customer segments.
• Discovering and fulfilling attractive requirements creates a wide range of possibilities for
differentiation. A product which merely satisfies the must-be and one-dimensional
3
- requirements is perceived as average and therefore interchangeable (Hinterhuber et al.,
1994).
• Kano’s model of customer satisfaction can be optimally combined with quality function
deployment. A prerequisite is identifying customer needs, their hierarchy and priorities
(Griffin and Hauser, 1993). Kano’s model is used to establish the importance of individual
product/service features for the customer’s satisfaction and thus it creates the optimal
prerequisite for process-oriented product development activities.
2.2 Satisfaction and customer loyalty
There have been extensive studies about the linkage between satisfaction and customer loyalty.
As many researchers suggest, customer loyalty is a combination of both behaviours and
attitudes (Dick and Basu, 1994; Oliver 1996; Allen and Rao, 2000; Jacoby, 1978). This means
that loyal customers are those who have a favourable attitude and repeated purchases as well.
Oliver (1996) defines loyalty as a strong commitment of customers that will repeat the purchase
or will continue to be customers of a product or a service in the future, no matter what the
impact of various situations or the efforts of marketing that aims to the change of customers’
purchase behaviour are. In most cases, customer satisfaction is a necessary but not sufficient
condition for loyalty. Satisfaction is directed specifically at product/service characteristics, and
may be relatively more dynamic measure. In contrast, customer loyalty is a broaden, more static
attitude toward a company in general, and it may include both rational and emotional elements.
In any case, it is generally accepted that loyalty is affected by customer satisfaction in direct or
indirect way (Vavra, 1997; Oliver 1996; Allen and Rao, 2000).
There are several types of loyalty according to the market conditions or the customer attachment
toward a product/service. Furthermore, different levels of customer loyalty exist in relation to
the degree of positive commitment (Hill, 1996). The most common acceptable measures of
loyalty are customer retention (repurchase intention) and willingness to recommend the
product/service to other consumers.
Of much interest is the work of Oliva et al. (1992, 1995) were there is an attempt to study and
analyse the correlation of customer loyalty with customer satisfaction, by using the basic
principles of catastrophe theory.
3. THE MUSA METHOD (Grigoroudis and Siskos, 2002)
The MUSA model is based on the principles of multicriteria analysis, using ordinal regression
techniques. The main objective of the MUSA method is the aggregation of individual judgments
into a collective value function via a linear programming disaggregation formulation. The
assumption is made that client’s global satisfaction depends on a set of criteria or variables
representing service characteristic dimensions.
According to the model, each customer is asked to express his/her preferences, namely his/her
global satisfaction and his/her satisfaction with regard to the set of discrete criteria. MUSA
assesses global and partial satisfaction functions Υ* and Χi* respectively, given customers’
judgments Υ and Χi. The method follows the principles of ordinal regression analysis under
constraints using linear programming techniques (Jacquet-Lagrèze and Siskos, 1982; Siskos and
Yannacopoulos, 1985; Siskos, 1985). The ordinal regression analysis equation has the following
form (Table 1 presents model variables):
4
- * n
Y = ∑ bi X i*
i =1
n (1)
b =1
∑ i
i =1
where the value functions Y * and X i* are normalised in the interval [0, 100], and bi is the
weight of the i-th criterion.
Table 1: Variables of the MUSA method
Y : client’s global satisfaction
α : number of global satisfaction levels
m
y : the m-th global satisfaction level (m=1, 2, ..., α)
n : number of criteria
Xi : client’s satisfaction according to the i-th criterion (i=1, 2, …, n)
αi : number of satisfaction levels for the i-th criterion
k
xi : the k-th satisfaction level of the i-th criterion (k=1, 2, ..., αi)
Y* : value function of Y
y*m
: value of the ym satisfaction level
X*i : value function of Xi
xi*k : value of the xik satisfaction level
The normalisation constraints can be written as follows:
y*1 = 0 , y*α = 100
*1 (2)
xi = 0 , xi = 100 for i=1,2 ,… ,n
*α
i
Furthermore, because of the ordinal nature of Y and X i the following preference conditions
are assumed:
y* m ≤ y* m +1 ⇔ y m ≺ y m +1 for m = 1,2 ,… ,α − 1
*k (3)
xi ≤ xi* k +1 ⇔ xik ≺ xik +1 for k = 1,2 ,… ,αi − 1
where ≺ means “less preferred or indifferent to”.
The MUSA method infers an additive collective value function Υ * , and a set of partial
satisfaction functions Χ i* from customers’ judgements. The main objective of the method is to
achieve the maximum consistency between the value function Υ * and the customers’
judgements Υ .
Based on the modelling presented in the previous section, and introducing a double-error
variable, the ordinal regression equation becomes as follows:
5
- n
~
Y * = ∑ bi Χ i* − σ + + σ − (4)
i =1
~
where Y * is the estimation of the global value function Y * , and σ + and σ − are the
overestimation and the underestimation error, respectively.
Equation (4) holds for customer who has expressed a set of satisfaction judgements. For this
reason a pair of error variables should be assessed for each customer separately (Figure 2).
Y*
100
...
σj+
y*m
σj-
...
y*2
Y
0
y1 y2 ... ym ... yα
Figure 2: Error variables for the j-th customer
Removing the monotonicity constraints, the size of the previous LP can be reduced in order to
decrease the computational effort required for optimal solution search. This is effectuated via
the introduction of a set of transformation variables, which represent the successive steps of the
value functions Υ * and Χ i* (Siskos and Yannacopoulos, 1985; Siskos, 1985). The
transformation equation can be written as follows (see also Figure 3):
zm = y
* m +1
− y* m for m=1,2 ,...,α − 1
(5)
wik = bi xi − bi xi for k=1,2,...,αi − 1 and i=1,2,...,n
* k +1 *k
It is very important to mention that using these variables, the linearity of the method is achieved
since equation (4) presents a non-linear model (the variables Υ * and Χ i* , as well as the
coefficients bi should be estimated).
6
- Y* Xi*
100 100
zα-1 wiα i −1
...
...
bi
y*m xi*k
...
...
z2 wi 2
y*2
bi
z1 xi*2 wi1
Y bi Xi
0 0
y1 y2 ... ym ... yα xi1 xi2 ... xik ... xiαi
Figure 3: Transformation variables zm and wik in global and partial value functions
According to the aforementioned definitions and assumptions, the basic estimation model can
be written in a linear program formulation as it follows:
M
[min]F = ∑σ
j =1
+
j +σ −
j
under the constraints
n t ji −1 t j −1
∑ ∑ w −∑ z
i =1 k =1
ik
m =1
m − σ + + σ − = 0 , for j = 1,2,..., M
j j
a −1
∑z
m =1
m = 100 (6)
n ai −1
∑∑ w
i =1 k =1
ik = 100
z m ≥ 0 , wik ≥ 0 , ∀m, i, k
σ + ≥ 0 , σ − ≥ 0 , for j = 1,2,..., M
j j
where M is the number of customers.
The preference disaggregation methodology consists also of a post optimality analysis stage in
order to face the problem of multiple or near optimal solutions. The MUSA method applies a
heuristic method for near optimal solutions search (Siskos, 1984). The final solution is obtained
by exploring the polyhedron of near optimal solutions, which is generated by the constraints of
the above linear program. During the post optimality analysis stage of the MUSA method, n
linear programs (equal to the number of criteria) are formulated and solved. Each linear
program maximizes the weight of a criterion and has the following form:
ai −1
[max]F ′ = ∑ wik , for i = 1,2,..., n
k =1
under the constraints
7
- F ≤ F* +ε (7)
all the constraints of LP (6)
where ε is a small percentage of F*.
The average of the optimal solutions given by the n LPs (7) may be considered as the final
solution of the problem. The model provides collective global and partial satisfaction functions
as well as average satisfaction indices and weights that represent the relative importance of each
criterion/subcriterion.
4. MODELLING PREFERENCES FOR CRITERIA IMPORTANCE
In order to model customers’ preferences, customers are asked, via a specialized questionnaire,
to place each one of the satisfaction criteria in one of the following categories: C1 = very
important criterion, C2 = important criterion, C3 = less important criterion.
Considering that C1, C2, C3 are ordered in a 0 to 100% scale, there are two preference thresholds
T1 and T2, which define the % rate, which distinguishes each one of the three categories (see
Figure 4).
C3 C2 C1
0% T2 T1 100%
Figure 4: Clauses of customers’ importance preferences
4.1 Weight estimation using ordinal regression techniques
The main purpose of this approach is the comparative analysis between the derived importance
of the criteria through the MUSA method and the stated importance given by the customers. In
order to estimate the stated importance of the criteria, which is a qualitative variable, a linear
program is formulated. The program calculates the two preference thresholds T1, above which a
criterion is considered very important, and T2, below which a criterion is considered less
important. In this way, the importance of each criterion according to customers’ preferences can
be assessed and compared with the results of the MUSA method.
For each criterion i =1,2,..n and each customer j = 1,2,..., M (where M is the number of
customers and n is the number of criteria) we set the following constraints:
• ˆ
If bij ∈ C1, that is customer j considers criterion i ‘very important’ then:
a −1
i
∑w
t =1
it -100 Τ1 + Sij+ ≥ 0
• ˆ
If bij ∈ C2, that is customer j considers criterion i ‘important’ then:
a −1
i
∑w
t =1
it -100 Τ1 - Sij- ≤ 0
8
- a −1
i
∑w
t =1
it -100 Τ2 + Sij+ ≥ 0
• ˆ
If bij ∈ C3, that is customer j considers criterion i ‘less important’ then:
a −1
i
∑w
t =1
it -100 Τ2 - Sij- ≤ 0
where Sij+ and Sij- are the overestimation and underestimation error, respectively, for the i-th
criterion of the j-th customer, C1, C2, C3 are the customers’ preference categories, T1 and T2 are
the preference thresholds, αi is the number of satisfaction scale levels for i criterion, and wit is a
MUSA variable.
The final linear program is:
[min] ∑∑ S j i
+
ij
−
+ S ij
under the constraints
ai −1
∑w
t =1
it
+ ˆ
− 100T1 + S ij ≥ 0, bij ∈ C1
ai −1
∑w it
−
− 100T1 − S ij ≤ 0
t =1 ˆ
bij ∈ C 2 ∀ i = 1,2,..., n and j = 1,2,..., M (8)
ai −1
∑w
t =1
it − 100T2 + S ≥ 0 +
ij
ai −1
∑w
t =1
it
− ˆ
− 100T2 − S ij ≤ 0, bij ∈ C 3
n ai −1
∑∑ w
i =1 k =1
ik = 100
T2 ≥ λ
T1 − T2 ≥ λ
After the solution of LP (8) a post optimality analysis follows, where n linear programs (equal
to the number of criteria), are formed and solved. Those linear programs maximize the weights
bi of the criteria and have the following form:
ai −1
[max]F ′ = ∑ wik , for i = 1,2,..., n
k =1
under the constraints
F ≤ F* +ε (9)
all the constraints of LP (8)
9
- where F*is the optimal solution of the objective function of LP (8) and ε is a small percentage of
F*.
4.2 Extension of the MUSA model
The main purpose of this analysis is to examine whether additional information about the
weights of the criteria can improve the results of the MUSA method. The examination of
possible improvement is done through the Average Stability Index (ASI). ASI is the mean value
of the normalized standard deviation of the estimated weights bi and is calculated as follows:
2
n
( )
n
n∑ bi − ∑ bi j
j 2
1 n j =1
ASI = 1 − ∑
j =1
, where bi j is the estimated weight of the criterion i, in
n i =1 100 n − 1
the j-th post-optimality analysis LP (Grigoroudis and Siskos, 2002).
At first, it is examined the following Mulltiobjective Linear Programming (MOLP) problem:
M
[min] F1 = ∑σ
j =1
+
j +σ −
j
[min] F2 = ∑∑ S
j i
+
ij
−
+ S ij
under the constraints
all the constraints of LP (6)
all the constraints of LP (8) (10)
In a Mulltiobjective problem it is pointless to try to find out a solution which will optimize all
the criteria of the objective functions simultaneously, considering that, in most of the cases, the
criteria are competitive, that is the optimal value of one criterion is not optimal for the other. A
basic tool for the representation of the competitiveness among multiple objective functions is
the pay-off matrix. This table represents the values that the multiple objective functions take
when optimizing the value of one of these objective function.
This multiobjective problem could be solved according to any MOLP method. Here the
following heuristic method is chosen:
Stage A: Solution of the following linear program
M
min] F1 = ∑σ
j =1
+
j +σ −
j
under the constraints
all the constraints of LP (6)
all the constraints of LP (8) (11)
Stage B: Minimize Sij+ and Sij- errors through LP (12):
10
- [min] F2 = ∑∑ S
j i
+
ij
−
+ S ij
under the constraints
F1 ≤ F1 + ε 1
*
all the constraints of LP (6)
all the constraints of LP (8) (12)
where F1* is the optimal solution of the objective function of LP (11) and ε is a small percentage
of F1*.
Stage C: At this post-optimality analysis stage n linear programs are formed and solved, one for
each of the n satisfaction criteria. Those linear programs maximize the bi of each criterion:
ai −1
[max]F ′ = ∑ wik , for i = 1,2,..., n
k =1
under the constraints
F1 ≤ F1 + ε 1
*
F2 ≤ F2 + ε 2
*
all the constraints of LP (6)
all the constraints of LP (8) (13)
where ε1 and ε2 are small and positive numbers, F1* and F2* are the optimal solutions of the
objective functions of LP (11) and LP (12), respectively.
5. ANALYSIS OF THE RESULTS
5.1 Dual Importance Window
In order to examine the relation between the stated and derived importance, a diagram, which
combines the derived importance of the criteria, calculated by the MUSA method, and the stated
importance, given by the customers, is created (Figure 5). In quadrants II and I appear the
dimensions that are truly important to the customers. Those are the main characteristics that
management and production should focus on. In quadrants IV and I appear the important
dimensions according to the customers’ free statement. Those are the dimensions that marketing
should focus on. When a characteristic appears in quadrant III or I there is an agreement
between derived and stated importance. That is both MUSA and the customers consider a
characteristic of quadrant I (III) of high (low) importance. On the other hand, in quadrants II or
IV there is a disagreement between the stated and derived importance. This disagreement is an
indication that those dimensions demand for further analysis.
The diagram in figure 4 can also be interpreted as a ‘Dual Importance Window’ (Lowenstein,
1995). Such an approach agrees with the approach of Kano’s model and its three basic
categories of product/service requirements. Quadrants III and I correspond to the characteristics
that are truly important or truly unimportant for the customers (one-dimensional characteristics).
Both the model and the customers agree on them giving the company a more valid view. In
11
- quadrant II appear the characteristics that the model rates as very important, but the customers
as less important, when they are asked straightforward. Those characteristics are called
‘unspoken motivators’ and represent dimensions to which the company should pay attention.
They may affect the future clientele, positively or negatively, although the customers consider
them of low importance. Finally in quadrant IV appear the characteristics that the model rates as
less important, but the customers as very important. These usually include expected or cost-of-
entry services, such as the guarantee that a product is expected to give for its products. A
company should keep such characteristics at a level at least as high as of the competitive
companies in order to keep its clientele, or offer extra, unexpected services to gain competitive
advantage.
IV
I
High
EXPECTED
(Truly important)
(Expected/cost of entry)
Stated Importance
L
NA
S IO
EN
IM
ED
ON II
III ATTRACTIVE
Low
(Truly unimportant) (Unspoken motivator)
Low High
Derived Importance
Source: ARBOR, Inc., 1991
Figure 5: Dual importance window
5.2 Customer Motivation Window (Lowenstain, 1995)
In true mathematical terms, the Customer Motivation Window is a correlation or simple
regression model, in which the score on each performance attribute (independent variable) is
correlated with an overall performance measure, such as intended future purchase with an
overall performance measure, such as intended future purchase or recommendation (dependent
variable), to see how they align. The dependent variable most representative of motivation
leading to action is purchase intent, or loyalty.
Importance in the Customer Motivation Window is calculated by the degree of correlation
between individual attribute ratings and the overall performance measure rating. This is done for
each customer, and modeled importance is the relationship of the attributes with how well they
correlate with the overall performance measurement ratings for all customers or a customer
segment.
Importance and priority is expressed by placement of attributes in quadrants on a graphic.
Quadrants can be described as follows (figure 6):
12
- • Quadrant I – high attribute performance scores/high correlation with positive intended
action (likelihood to remain loyal). These are attributes of high (probable) positive leverage
for the company that they should continue to emphasize.
• Quadrant II – high attribute performance scores/low correlation with positive intended
action (likelihood to remain loyal). These attributes, while performed well, have relatively
little leveraging impact on motivation for intended action. This may be a communication
issue for the company or it may simply be one of those expected attributes that must be
performed but not be improved.
• Quadrant III – low attribute performance scores/low correlation with negative intended
action (likelihood to remain loyal). These are the attributes that provide little value to the
customer or the company. If possible, the company should downscale or even eliminate
activities in these areas. Though not well performed, customers are relatively unlikely to
miss them.
• Quadrant IV - – low attribute performance scores/high correlation with negative intended
action (likelihood to remain loyal). The low attribute performance ratings closely relate to
low likelihood to remain loyal, so the company must target attributes in this quadrant for
improvement.
IV I
High
Must Improve Highest Leverage
Modeled Importance
II
III Lowest priority for
Low
Less Important improvement
Low High
Quality Rating
Source: ARBOR, Inc., 1991
Figure 6: Customer motivation window
6. AN APPLICATION TO AN EDUCATIONAL ORGANISATION
The MUSA and the extension of MUSA methods were applied to an educational organization in
order to assess the students’ preferences and the differences of the results produced from the
two methods. The satisfaction criteria that were examined concern the provided services, the
educational process, the secretarial support, the additional services and the image of the
organization. The performed analysis concern:
13
- • Weights’ estimation through ordinal regression techniques – Its main objective is the
comparative analysis between the derived importance of the criteria, calculated through the
MUSA method, and the stated importance given by the customers.
• Extension of the MUSA method – Its main objective is the examination of the possible
improvements of the MUSA’s results with the introduction of additional information for the
weights of the criteria. The examination of this possible improvement is based on the
average stability index (ASI).
6.1 Results of the weight estimation model
Different values of λ for the two constraints T2≥λ and T1-T2≥λ of the linear program 8 (§ 4.1)
100
have been chosen. It is interesting to notice that these values should be λ ≤ % , where n is
n
the number of criteria. This is due to the maximum value which λ can take, considering that it
cannot exceed the weight that the criteria would have if they were all of equal importance. In the
current case study there are five criteria, therefore λ≤0.2. After many tests, the better results
appeared for λ=0.15. The final results of the weight estimation through ordinal regression
techniques, as well as the results of the MUSA model are presented in Table 2.
According to the weight estimation model, all the criteria have almost the same weight. This is
hardly a surprise, since the customers, when asked freely, have the tendency to rate everything
as very important (Naumann and Giel, 1995).
Table 2: Weight comparison between MUSA model and Weight estimation model
Criteria Weight estimation model MUSA
Provided services 22.752 33.300
Educational process 29.070 20.000
Secretarial support 16.467 20.000
Additional services 15.733 13.300
Image 15.977 13.300
The results of the two analyses were normalized and presented in a dual importance window
(Figure 7). According to figure 5, there is an agreement between the stated and the derived
importance for the criteria of the ‘Provided Services’, ‘Additional Services’ and ‘Image’. The
first is considered to be of high importance while the other two of low importance in both cases.
The criteria of ‘Educational Process’ and ‘Secretarial Support’ should be further examined since
they appear in between quadrants IV-I and III-II respectively. The educational organization
should focus the management efforts on ‘Provided Services’, ‘Educational Process’, and
‘Secretarial Support’ that are the truly important dimensions according to the MUSA model.
Moreover, it should focus the marketing efforts, mainly, on the ‘Educational Process’ and the
‘Provided Services’. These are the two most important criteria according to the customers’
stated opinion.
14
- Importance
High educational process
provided services
Stated
image
secretarial support
additional services
Low
Low Derived High
Figure 7: Dual importance window of the educational organization
Interpreting Figure 7 as a ‘Dual Importance Window’, we can see that the criterion of ‘Provided
Services’, which appears in quadrant I, and the criteria of ‘Image’ and ‘Additional Services’,
which appear in quadrant III, are one-dimensional attributes and represent the basic
requirements and desires of customers. This means that an increase in the performance of these
criteria will lead to a proportional increase of customer satisfaction. The criterion of
‘Educational Process’ lies between quadrant IV, where appear the attracted attributes, and
quadrant I, where appear one-dimensional (truly important) attributes. This means that it is quite
possible that a high performance in this particular criterion will not necessary imply a high
customer satisfaction index, while, in the contrary, a low performance can lead to high
dissatisfaction. On the other hand, the criterion of ‘Educational Support’ lies between quadrant
II, where appear the attractive attributes, and quadrant III, where appear one-dimensional (truly
unimportant) attributes. This means that it is quite possible that a high performance in this
particular criterion will lead to high satisfaction, while in the contrary, a low performance will
not necessary imply low dissatisfaction.
6.2 Results of the MUSA’s extension
The results of the MOLP problem described in paragraph 4.2 are presented in Table 3. It is
obvious that the two objective functions are highly competitive, as the minimization of each
function causes a high increase of the other.
Table 3: Pay-off matrix
F1 F2
[min] F1 0 3860
[min] F2 5160 90
After many tests for different values of λ, λ=0.1 has been chosen as the value that gave the best
results. The results of the heuristic method described in paragraph 4.2 with F1*≤10 and
F2*≤3036 are presented in table 4. Both MUSA and the extension of MUSA consider the criteria
15
- of ‘Provided Services’, ‘Educational Process’, and ‘Secretarial Support’ as the most important.
The only difference appears in the order with which each criterion is considered to be important.
While in the MUSA method the ‘Provided service’ criterion is considered as the most important
criterion and the ‘Educational Process’ follows in significance, the opposite holds for the
extension of MUSA. General speaking, both the MUSA method and the extension of MUSA
give results that are very similar. However, the increase of ASI shows that the extra information
included in the original MUSA method can improve its stability. As a conclusion, MUSA
extension can sometimes improve the MUSA model.
Table 4: Comparative results between MUSA extension and MUSA model
Criteria MUSA’s extension MUSA
Provided services
26.3 33.3
Educational process
39.1 20.0
Secretarial support
24.6 20.0
Additional services
8.0 13.3
Image
2.0 13.3
ASI 76.59% 72.55%
6.3 Analysis of customer loyalty
A further analysis for the examination of the relationship that the different type of attributes
(one-dimensional, expected, attractive) has with customer loyalty is attempted in this section.
Specifically, it is examined the correlation of the criteria with the intention of customers to reuse
the services of the particular educational organization. Considering that the data, which were
collected through a specialized questionnaire, are qualitative, the Spearman’s R and the
Kendall’s tau were chosen as the most appropriate indicators (Table 5).
Table 5: Correlation of criteria with the intention to reuse the services of the educational organization
Spearman’s R Kendall’s tau
Provided services 21% 19.9%
Educational process 31% 29.1%
Secretarial support 33.7% 31.6%
Additional services 20.5% 18.6%
Image 18.2% 16.5%
According to Table 5, the criteria of ‘Educational Process’ and ‘Secretarial Support’ that tend to
become expected and attractive attributes respectively, have the highest correlation with the
reuse intention. On the other hand, the one-dimensional characteristics seem to be of less
importance with regard to the reuse intention.
With respect to the customer motivation window of Figure 8, which combines the performance
of each one of the criteria and their relationship with the reuse intention, it can be observed that
the criteria of ‘Educational Process’ and ‘Secretarial Support’ are the attributes of high
(probable) positive leverage for the company. These are the criteria that the organization should
continue to emphasize. The ‘Additional Services’ and the ‘Image’ criteria, which are the truly
unimportant criteria according to figure 7, are the ones that provide little value to the customers
of the organization and consider to be of less importance. Finally, the ‘Provided Services’
16
- criterion, which is a truly important criterion, according to figure 7, for customer satisfaction, is
the one that has the lowest priority for improvement as it has a high performance score but low
correlation with the reuse intention.
High
secretarial support
Modeled Importance
educational process
additional services
provided services
image
Low
Low Quality Rating High
Figure 10: Customer motivation window of the educational organization
7. CONCLUDING REMARKS
Real world examples have shown that free stated importance by the customer is often different
than derived importance by a preference disaggregation model. In this paper, an extension of the
MUSA methodology is presented. It allows modelling customer importance preferences for
service characteristics and offers the ability to compare derived and modelled weights of the
satisfaction dimensions. The results of MUSA extension application to an educational
organization, give a representative example of the differentiation between derived and stated
importance.
References
Allen D.R. and Rao T.R. (2000). Analysis of customer satisfaction data, ASQ Quality Press,
Milwaukee.
Berger C., Blauth R., Boger D et al. (1993). Kano’s methods for understanding customer-
defined quality, The Journal of the Japanese Society for Quality Control, Fall, pp. 3-35.
Dick A. and Basu K. (1994). Customer loyalty: Toward an integrated conceptual framework,
Journal of the Academy of Marketing Science, 22, (2), 99-113.
Griffin A. and Hauser J.R. (1993). The voice of the customer, Marketing Science, Winter, pp. 1-
27.
Grigoroudis E. and Siskos Y. (2002), Preference disaggregation for measuring and analysing
customer satisfaction: The MUSA method, European Journal of Operational Research, (to
appear).
Hill N. (1996). Handbook of customer satisfaction measurement, Gower Publishing, Hampshire.
17
- Hinterhuber H.H., Aicher H. and Lobenwein W. (1994). Unternehmenswwert und Lean
Management, Manz-Verlag, Vienna.
Jacoby J. (1978). Brand loyalty: Measurement and management, Wiley, New York.
Jacoby Jacob, (1978), ‘Brand Loyalty: Measurement and Management’, Wiley, New York.
Jacquet-Lagrèze E. and J. Siskos (1982). Assessing a set of additive utility functions for
multicriteria decision-making: The UTA method, European Journal of Operational Research,
(10), 2, 151-164.
Kano N. (1984). Attractive quality and must-be quality, The Journal of the Japanese Society for
Quality Control, April, pp. 39-48.
Lowenstein M.W. (1995). Customer Retention – An integrated Process for Keeping Your Best
Customers, ASQC Press, Milwaukee.
Matzler K. and Hinterhuber H.H. (1998). How to make product development projects more
successful by integrating Kano’s model of customer satisfaction into quality function
deployment, Technovation, vol. 18, no. 1, pp. 25-38.
Matzler K., Hinterhuber H.H., Bailom F. and Sauerwein E. (1996). How to delight your
customers, Journal of Product and Brand Management, vol. 5, no. 2, pp. 6-18.
Naumann E. and Giel K., (1995), ‘Customer Satisfaction Measurement and Management: Using
the voice of the customer’, Thomson Executive Press, Cincinnati.
Oliva T.A., Oliver P.L. and Bearden W.O. (1995). The relationships among consumers
satisfaction, involvement, and product performance: A catastrophe theory approach, Behavioral
Science, 40, 104-132.
Oliva T.A., Oliver P.L. and McMillan I.C. (1992). A catastrophe model for developing service
satisfaction strategies, Journal of Marketing, 56, 83-95.
Oliver R. L. (1996). Satisfaction: A behavioral perspective on the customer, McGraw-Hill, New
York.
Siskos Y. (1984). Le traitement des solutions quasi-optimales en programmation linéaire
continue: Une synthèse, RAIRO Recherche Opérationnelle, 18, 382-401.
Siskos Y. (1985). Analyses de régression et programmation linéaire, Révue de Statistique
Appliquée XXXII, 41-55.
Siskos Y. and D. Yannacopoulos (1985). UTASTAR: An ordinal regression method for
building additive value functions, Investigaçao Operacional, (5), 1, 39-53.
Siskos Y., (2000), ‘Linear Programming’, New Technologies, Athens.
Tsiotras G., (1995), ‘Quality Improvement’, Benou Publishing, Athens.
Vavra T.G. (1997). Improving your measurement of customer satisfaction: A guide to creating,
conducting, analyzing, and reporting customer satisfaction measurement programs, ASQC
Quality Press, Milwaukee.
18
nguon tai.lieu . vn