Customised Customer Support Using a Soft Computing Approach 
S Shah  
Cranfield University 
s.shah@cranfield.ac.uk 
R Roy 
Cranfield University 
r.roy@cranfield.ac.uk 
A Tiwari 
Cranfield University 
a.tiwari@cranfield.ac.uk
B Majeed 
BT Plc 
b.majeed@bt.com 
Abstract 
This paper describes the research and development 
of a methodology to identify the type of information 
required by the service advisor (CSA) within customer 
contact centre (CCC) environment. Data was collected 
through case studies carried out within five customer 
contact centres to derive the categories for customers 
and advisors based on demographic, experience, 
business value and behavioural attributes. We provide 
the methodology to develop a fuzzy expert system 
which assigns a new customer or advisor to the pre-
defined categories. The authors have explained the 
steps which were followed for the development of the 
fuzzy expert system. A prototype system has been 
designed and developed to identify the type of customer 
and CSA based on the demographic, experience and 
behavioural attributes. The authors illustrate analysis 
with real data, based on the work with large scale 
customer contact centres. Validation of the information 
requirement model was carried out at the contact 
centres.  
1. Introduction 
In a time of fast growing technology and 
communication systems, it is important for industry 
and organisations to develop new customer contact 
centre (CCC) environment technologies for better 
customer satisfaction. There are three features of 
contact centre operations that customers feel are crucial 
to quality service, namely convenience in fast call 
handling, cordiality of the advisor, and consistency in 
advisors providing a reliable and accurate service [1]. 
It is critical for companies to identify the need to offer 
a superior service in order to ensure business survival 
in a service sector economy [2]. Customer contact 
centres afford the companies the potential to manage 
customer relations more effectively, thus providing 
some competitive advantage while saving costs [3]. 
Customer satisfaction may in addition be based on 
another three dimensions: access, including the 
advisors communication skills; timeliness, including 
advisors resolution of queries; and quality, which 
includes the accuracy, consistency and 
comprehensiveness of the advisors advice, in addition 
to the knowledge and politeness of the advisors. Thus 
the role of the advisors, assumes a heightened 
importance in customer satisfaction [4]. Within the 
current contact centre environment there is a problem 
of high staff turnover and lack of trained staff at the 
right place for the right kind of customer. Business 
needs to assign any available advisor to a customer and 
provide consistent and good quality of service. There is 
a need to identify the right amount of information to be 
displayed on the screen considering both the customer 
and the assigned advisor background.
2. Related Research 
Research in understanding customer preferences, 
known as ‘consumer behaviour study’, has been the 
subject of investigation in psychological marketing 
area for few decades. Understanding and adapting to 
changes of customer behaviour is an important aspect 
of surviving in a continuously changing environment 
[6]. Customer choice of a product depends on explicit 
requirements, implicit requirements, available options 
and latent requirements implied by the product [7]. 
The performance of a CSA during interactions with 
customers has been the subject of considerable 
research, in both sales and service settings [8]. 
Research has suggested that advisors (CSA’s) 
performance is critical to create customer satisfaction, 
little has been done to analyse which employee 
behaviour influence customer encounter satisfaction 
and which behaviour influence relationship 
satisfaction. Previous studies also suggest that 
attitudinal and behavioural responses of advisors are 
important because of the interactive nature of service 
delivery. It also showed that advisors attitudinal and 
behavioural responses can positively and negatively 
affect customer’s perceptions of the service encounter 
and their judgments of service quality [9]. Trust has a 
moderate but beneficial influence on the development 
Proceedings of the 2005 International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on 
Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’05) 
0-7695-2504-0/05 $20.00 © 2005 IEEE 
of positive customer attitudes, intentions, and 
behaviour. Advisors (CSA) have modest influence 
over the development of trust between themselves and 
their customer [9]. Customer attitude is influenced by 
belief about brand equity (value), which is affected by 
the content, context and infrastructure. Customer 
loyalty is determined by attitude and belief about the 
context in which the products or services are offered 
[10]. Modeling the users can include statements of 
how the users within a specific user group behave in 
certain situations or perform certain functions [11]. 
Emotional reactions to a sales interaction may affect 
consumer satisfaction with the purchase experience 
and future purchase intentions (cross – up sell 
opportunities) [12].  
Soft computing differs from hard (conventional) 
computing in that it is tolerant of imprecision, 
uncertainty and partial truth [13]. Soft computing 
technologies provide an approximate solution to an ill 
defined problem and can create user models in an 
environment such as contact centre to identify: (a) 
customer willingness to buy (b) companies prediction 
towards customer purchase intentions (c) advisor 
reaction towards customer attitude and (d) customer 
behaviour towards advisors communication [14]. 
3. Current Practice 
For the purpose of this research, the authors 
organised visits to three different customer contact 
centres (CCC) and interviewed 20 advisors and 6 team 
leaders. The data and information collected from these 
centres were captured, understood and were combined 
with the current information obtained from the literature 
review and, they were used to identify the categorisation 
for customer and advisor. The main objectives were:  
ƒ Identify the current understanding of the 
customer contact centre environment, its overall 
operation and working. 
ƒ Identify the current bottlenecks in the business 
process.  
ƒ Identify the use of different customer – advisor 
characterisation procedures. 
3.1. Key Observations and Findings 
The primary key targets for the centres noticed by 
the authors were mainly the RAP time which is the 
time the advisor spent other than on calls. Call times 
takes up about 2 minutes to 12 minutes. Call Handling 
Time is the effective time; the advisor spends on calls 
with the customers. The findings showed that there 
was a high turn over of CSA and it was necessary to 
allocate the first available advisor to the customer and 
then provide the advisor with relevant information. 
The technical issues encountered during the visits to 
the centres are as discussed below in table (1). 
Table1. Contact Centre Observations and 
Findings 
Issues Company A  Company B Company 
C
System 
Functiona
lities 
Complex 
systems.  
Long time 
needed on 
training  
Wrong 
calls 
transferred 
through 
IVR. 
Advisor 
(CSA) 
Overview 
Time spent on 
arrangement 
of work once 
the call is 
finished 
Wrong calls 
been dealt by 
the advisor 
More time 
spent on 
search of 
information 
Customer 
Overview 
Understand 
the delay  
Unsure the type 
of problems 
encountered.  
Lack of 
sufficient 
information  
Call 
Problems 
Customer 
calls without 
knowing the 
service 
required. 
Wrong 
department calls 
which are 
needed to be 
transferred. 
Long 
queues of 
calls with 
long wait 
times 
4. Cranfield Approach – Research      
    Methodology 
Through the proposed methodology for 
categorisation of customer and advisor, the authors 
have demonstrated a way which can help to identify 
the right amount of information which can enable the 
advisor to deal with the customer more efficiently and 
thus providing better customer satisfaction. The main 
sections which are discussed here for the development 
of the information requirement methodology are: 
1. Data Collection – Study to identify the 
industrial context and need for information 
requirement framework. 
2. Clustering Analysis – For categorisation of 
customer and advisor. 
3. Development of Fuzzy Expert system –.For 
assigning any customer and advisor with a pre-
defined category.  
4. Information Requirement Analysis – To 
identify the required information to be 
displayed on the screen depending on the 
customer and advisor  
Proceedings of the 2005 International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on 
Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’05) 
0-7695-2504-0/05 $20.00 © 2005 IEEE 
Figure 1. Flowchart for the proposed 
methodology 
AS-IS study was done at five of the customer contact 
centres to identify the current trends in customer 
contact and the need to identify the right amount of 
information considering both the customer and 
assigned advisor background. Data was collected with 
semi structured questionnaire for advisors and team 
leaders at contact centres. Proper methodology was 
followed for the development of fuzzy expert system 
for the assignment of category to the advisor and 
customer. Experimental results were carried out within 
the model to identify the type of category assigned to 
each customer and advisor which was validated with 
the experts.  For full explanation of the development 
of the methodology refer to reference [16].  
For information requirement analysis; possible 
combinations of {customer, advisor} scenarios were 
derived. Based on these possible scenarios, the 
minimum amount of information required to be 
displayed was derived. The team leaders and 
managers were thus given the option of all the 
possible combinations of the customer and advisors, 
and asked to identify information which would help 
the advisor to serve the customer. Further design and 
development of the information required framework is 
discussed in section 4.4. Validation of information 
requirement framework was done through expert 
judgments from team leaders and discussed in section 
5. 
4.1. Data Collection 
Data was collected with the help of semi-
structured questionnaires for advisors (CSA) and team 
leaders/managers with respect to their demographic 
variables, experience and behavioural variables within 
five customer contact centre focusing on fault and 
sales and looking on single to multi profile business 
customers. A total of 84 advisors were interviewed 
and assessed, 60 customer calls were monitored, and 
total of 19 team leaders and managers were 
interviewed through the questionnaires. The key 
observations which the authors noticed for the data 
collection were advisors characteristics and customer 
monitoring (voice). Please refer to reference [16] for 
full list of the criteria’s used for customer and advisor 
data collection. The customer data collection was done 
on the basis of the information provided on the screen 
of the advisor when the call conversation was in 
progress. Based on the data collection and analysis of 
data; attributes derived for customer and advisor are as 
follows: 
ƒ Customer – age, education, financial status, 
time with company, business value and 
behavioural analysis.  
ƒ Advisor – age, education, experience, previous 
experience, IT speed, and behavioural analysis.  
Through the data analysis tool, the customers and 
advisor were then grouped according to the attributes 
shared among each other.  
4.2. Clustering Analysis – Identification of    
 Customer and Advisor Categorisation 
This section shows the method followed for 
identification of customer and advisor categorisation 
through clustering analysis by using two – step 
process within SPSS analysis. The final set of 
attributes used for customer and advisor (CSA) for the 
clustering analysis to derive the categories are as 
shown in table (2). Six advisor categories (A1-A6) 
were derived out of the 84 data sets for the advisors. 
Based on the clustering few results were noted which 
were: 
1. Because the number of clusters increased from 
6-10, the total number of cases each cluster is 
taking is not properly distributed. 
2. The rules derived from the cluster results are 
repeated and are too close to each other. 
Proceedings of the 2005 International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on 
Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’05) 
0-7695-2504-0/05 $20.00 © 2005 IEEE 
TABLE 2. 
ADVISOR AND CUSTOMER ANALYSIS [16] 
4.3. Development of Fuzzy Expert System 
This section discusses the steps followed for the 
development of the fuzzy expert system to assign any 
customer and advisor to that of pre-defined category 
which was derived from the clustering analysis. 
Step 1 – Identify the critical factors and define 
membership functions and fuzzy sets. 
The critical factors were the input variables of the 
fuzzy ES which were as age, gender, and education, 
and financial background, time with the company, 
business value and behaviour from the customer side 
which would identify the type of category they belong 
to. Triangular and trapezoidal types of membership 
function are selected to define the variables (figure 2). 
Step 2 – Construct the Fuzzy Rules 
Within the fuzzy expert system model once the 
membership functions for customers and advisors 
were derived, fuzzy if…then rule were written which 
identified the type of input for customers and advisors. 
The rule base specifies qualitatively how the output of 
the system “Category” for the advisor and the 
customer is determined for the input variables of Age, 
Education, Financial Status, and Time with Company, 
Business Value, and Experience. A total of twenty 
rules were derived within the expert system. For 
advisor rules; IF age is young, education is school, 
experience is novice, previous exp is low, IT speed is 
slow, positive behaviour as friendly and negative 
behaviour as unaware THEN the selected category is 
A1. 
For customer rules; IF age is young, education is 
school, financial status is poor, time with company is 
low, business value is low, positive behaviour is none 
and negative behaviour is aggressive THEN the 
category selected is C1. 
4.4. Information Requirement Analysis 
Information requirement analysis was done on the 
basis of the set of categories for customer and advisor 
derived from the clustering and determined from the 
fuzzy expert system model. The main objective was to 
identify the minimum amount of information which is 
required to be displayed on the screen to the advisor 
which would enable the advisor to help the customer. 
This information should always satisfy the three 
important business aspects of customer contact which 
were (i) Customer Satisfaction, (2) Resolving the 
conflict and (3) Cross Sell – Up Sell opportunities. 
Information Requirement framework was developed 
to overcome the information overload with the current 
contact centre environment. Also from the point of 
customer satisfaction speed of response was crucial 
and the right amount of information which is required 
to be displayed to the advisor under particular 
customer – advisor situation was important. 
Advisors (CSA) 
1. Age – young, middle age, old 
2. Education – school, college, graduate, professional 
3. Experience – novice, medium, senior 
4. IT Speed – slow, medium, fast 
5. Previous Exp – low, moderate, extensive 
6. Positive Behaviour – attentive, friendly, customer focus 
7. Negative Behaviour – unaware, annoyed, angry 
Customer 
1. Age – young, middle age, old 
2. Education – school, college, graduate, professional 
3. Financial Status – poor, average, good 
4. Time with Company– low, moderate, high 
5. Business Value – low, medium, high 
6. Positive Behaviour – joyful, co-operative, understanding 
7. Negative Behaviour – angry, annoyed, aggressive 
Figure. 2. Sample Membership Functions for 
Input (Age) and Output (Categories) of the 
System [15] 
Proceedings of the 2005 International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on 
Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’05) 
0-7695-2504-0/05 $20.00 © 2005 IEEE 
Figure 3. Conceptual Contact Centre Model 
From the initial understanding of the contact centre, 
and from the literature studies; the author designed a 
template with the complete list of information which 
would be used during a particular customer-advisor 
conversation. This list is mainly divided into three 
sections with customer information, business service 
details and advisor details (figure 4). Once the total 
information to be displayed was known, it was 
validated with the industry experts of six team leaders 
and three advisors within the centre. 
5. Validation 
The information and the results from the model 
were verified through team leaders and managers at 
three of the contact centres. A total of nine team 
leaders and managers were interviewed with the help 
of an open set questionnaire, showing the categories 
derived and the assignment of a particular customer or 
advisor to these categories through the help of the 
fuzzy expert system tool developed. From the 
validation, it was noticed that the expert judgment did 
correspond to that of the results from the expert system 
model framework for 80% of the overall experiments 
that were carried out. A total of thirty six scenarios 
were considered identifying the best case and worst 
case of customer and advisor contact. The scenario 
identifies the type of customer and advisor and selects 
the required information based on the customer and 
advisor attributes from the categorisation [16]. 
Example 1. Worst Advisor – Best Customer Scenario 
(Advisor A1 and Customer C4)
A1 – Female, 18-25, School (education), >1yrs 
Experience, Slow (IT speed), None Previous 
experience, Angry and Unaware (behaviour) 
C4 – Female, 40+ (age), Professional (education), 
Average (financial status), 10-12 yrs (time with 
company), High (business value), Joyful (behaviour) 
Information to Display - Customer ID, address details, 
customer type, time with company, buying 
pattern/power, financial status, type of services, 
payment options, new products and services
Example 2. Best Advisor – Worst Customer Scenario 
(Advisor A5 and Customer C1)
A5 – Male, 50+ (age), Professional (education), 10+ 
yrs (experience), Medium (IT speed), Moderate 
(prev.exp.), Friendly (behaviour) 
C1 – Female, 18-25, School (education), Poor 
(financial status), 1-5 yrs (Time with company), Low 
(business value), Angry and Aggressive (behaviour) 
Information Display - Customer ID, address details, 
type of customer, payment options, financial status, 
type of services, business value to company, customer 
complaints 
6. Discussion and Future Research 
The authors have demonstrated the steps which 
were followed to identify the information requirement 
analysis for the advisor within contact centre 
environment.  The need to identify the right amount of 
information to be displayed on the screen for both 
customer and the assigned advisor background led to 
the development of the research framework.  
Experimental results were carried out which showed 
that 80% of time the model was assigning a particular 
customer and advisor to the [16]. The cost and 
maintenance analysis of the framework would be 
considered for future research and will form the part of 
the continuing research carried out within the project. 
Further validation of the framework will be carried out 
with simulation techniques.  
Advisor Details 
Company Value 
New Products 
Last Advisor Details 
Account Update 
Change of Services 
Product Update 
Customer 
Information 
Customer ID Details 
Type of Customer 
Address Details 
Demographic Data 
Business Details 
Type of Service 
Time with Company 
Previous Transactions 
Behavioural Changes 
Financial Status 
Buying Power 
Complaint Details 
Figure 4. Contact Centre Information 
Proceedings of the 2005 International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on 
Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’05) 
0-7695-2504-0/05 $20.00 © 2005 IEEE 
7. Conclusions 
This paper is focused on the research and 
development of methodology to identify the right 
amount of information to be displayed on the screen. 
Four main approaches were followed for the 
development of the information requirement 
methodology. The AS-IS study was carried out to 
study and identify the industrial context and the need 
of the framework. The authors identified the initial 
attributes through five case studies carried out at the 
customer contact centres within UK ranging from 
telecoms to help desk and government with 84 
customer advisor and 60 customers’ data points. Based 
on the initial clustering results, the authors then derived 
the initial categorisation for customers and advisors. 
Development of fuzzy expert system was carried out to 
assign any customer or advisor to that of the pre-
determined category from the clustering analysis. The 
fuzzy expert system was validated with the experts 
from CC with experimental results showing the 
assignment of the categories to customer and advisors. 
Information requirement framework was validated with 
nine team leaders and advisors at the contact centres.  
8. Acknowledgments 
The authors wish to acknowledge the support of the 
Engineering and Physical Sciences Research Council 
(EPSRC), British Telecommunication Plc, and 
Decision Engineering research team (DEG) in the 
Enterprise Integration department at Cranfield 
University; UK 
9. References 
[1] Haymarket Business Publications (1998). The 
telebusiness report – the definitive report on 
telebusiness in the UK to the year 2005. Marketing 
Direct Magazine. April 1998. PP 5-17 
[2] Prabhaker, R; Sheehan, J; Coppett, J (1997). The 
power of technology in business selling: call centres. 
Journal of Business and Industrial Marketing. Vol 
12. Issue ¾. PP 220-232 
[3] Connon, E (1996). Developing and retaining 
profitable customer relationships through call 
centres. Direct Marketing. Vol 59. Issue 5. PP 24-26 
[4] Brown, Gavin and Maxwell, Gillian (2002) 
Customer service in UK call centres: organisational 
perspectives and employee perceptions. Journal of 
Retailing and Consumer Services Vol 9 2002 PP 
309-316 
[5] Schmitt, M and Allscheid, S (1995) Employee 
attitudes and customer satisfaction: making 
theoretical and empirical connection. Personnel 
Psychology. Vol 48. Issue 3. PP 521-36. 
[6] Chiu, Chaochang (2002). A case based customer 
classification approach for direct marketing. Expert 
Systems with Applications. Vol 22 (2002). Pp 163-
168. Elsevier Science Ltd. 
[7] Fung, R.Y; Popplewell, K and Xie, J (1998). An 
intelligent hybrid system for customer requirements 
analysis and product attribute targets determination. 
International Journal of Production Research. 1998. 
Vol 36. No.1. PP 13-34.  
[8] Zeelenberg, Marcel and Pieters, Rik (2004). Beyond 
valence in customer dissatisfaction: A review and 
new findings on behavioural responses to regret and 
disappointment in failed services. Journal of 
Business Research. Vol 57 (2004). Pp 445-455. 
Elsevier Science Ltd. 
[9] Dolen, Willemijn van; Ruyter, Ko de and Lemmink, 
Jos (2004). An empirical assessment of the influence 
of customer emotions and contact employee 
performance on encounter and relationship 
satisfaction. Journal of Business Research. Vol 57 
(2004). Pp 437-444. Elsevier Science Ltd. 
[10]  Swan, J; Bowers, M and Richardson, L (1999). 
Customer trust in the salesperson: An Integrative 
review and meta-analysis of the empirical literature. 
Journal of Business Research, Vol 44, Issue 2. PP 
93-107 
[11] Bushey, R.; Mauney, Jennifer. M and Deelman, 
Thomas (1999). The development of behaviour-
based user models for a computer system. 7th
International Conference on User Modeling 
(UM99). 20th -24th June 1999. Banff Centre, Banff. 
Canada. Pp 109-118.   
[12] Goff, Brent. G; Boles, James. S; Bellenger, Danny. 
N and Stojack, Carrie (1997). The influence of 
salesperson selling behaviours on customer 
satisfaction with products. Journal of Retailing. Vol 
32. No 2. pp 171-183.  
[13] Zadeh, L. (1996). The role of soft computing and 
fuzzy logic in conception, design and deployment of 
intelligent systems. Proceedings International 
Workshop on Soft Computing in Industry, Muroran, 
Japan, April 1996, pp 136-137. 
[14] Ngai, E.W.T and Wat, F.K.T (2003). Design and 
development of a fuzzy expert system for hotel 
selection. The International Journal of Management 
Science. Vol 31. PP 275-86. Elsevier Science. 
[15] Shah, Satya; Roy, Rajkumar and Tiwari, Ashutosh 
(In Press).  Development of fuzzy expert system for 
categorising customer and advisors in contact 
centres.  Submitted to 10th Online World Conference 
on Soft Computing in Industrial Applications.  
[16] Shah, Satya; Roy, Rajkumar; Tiwari, Ashutosh and 
Basim Majeed (Unpublished). Categorisation of 
customer and advisor in contact centres. Submitted 
to European Journal of Operational Research. 
Proceedings of the 2005 International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on 
Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’05) 
0-7695-2504-0/05 $20.00 © 2005 IEEE