Customer segmentation for a mobile telecommunications company based on service usage
•
6 likes•7,078 views
Competition between the mobile operators is becoming more based on subscriber’s behavior. In order to improve mobile operator’s competitiveness and customer value, several data mining technologies can be used.Most telecommunications carriers cluster their mobile customers by billing system data. This paper discusses how to cluster mobile customers based on their call detail records and analyze their consumer behaviors.
1 of 6
Download to read offline
1
2
3
4
5
6
More Related Content
Customer segmentation for a mobile telecommunications company based on service usage
1. Customer Segmentation
For a Mobile Telecommunications Company
Based on Service Usage Behavior
By:
Shohin Aheleroff
Advisor:
Dr. Gholamian
Jun 2011
Abstract: Competition between the mobile operators is
becoming more based on subscriber’s behavior. In order
to improve mobile operator’s competitiveness and
customer value, several data mining technologies can be
used. One of the most important data mining technologies
is customer clustering and segmentation. This targeting
practice has been proven manageable and effective for
mobile
telecommunications
industry.
Most
telecommunications carriers cluster their mobile
customers by billing system data. This paper discusses how
to cluster mobile customers based on their call detail
records and analyze their consumer behaviors. Finally, the
subscribers categorized in four loyal groups and the
strategy to apply has been suggested in a specific life cycle.
I. INTRODUCTION
Mobile operator’s profits and ARPU (Average Revenue Per
User) are facing great challenges. Customer’s demand and
requirements of services has been changed. In order to
improve mobile operator’s competitiveness and customer
value, several data mining technologies can be used. One of
most important data mining technologies is customer
clustering analysis to categorize potential customers into
distinct groups for distinctive contact strategies. With the rapid
growing marketing business, data mining technology is imply
more important role in the demands of analyzing and utilizing
the large scale information gathered from customers especially
large amount call detailed record of mobile customers.
Information about customer’s behavior is required to segment
and personalize products and services along with business
strategy and planning.
But most of them segment customers only by personal
information such as age, gender and address from special
points, rather than from their actual behavior. Furthermore,
one of the key purposes of customer segmentation is customer
retention to increase the loyalty and avoid churning. This
paper focused on proposing a customer segmentation
framework based on actual customer behavior.
II. Research methodology
This study is designed to discover the patterns of use for
mobile services based call/event detailed records including
major service usage information and not personal information.
There are many clustering method, for example, fuzzy
clustering method, system clustering method, dynamic
clustering method and K-means clustering method. But the Kmeans method of cluster detection is most commonly used in
practice that the number of clusters is an input. Based on
business and infrastructure constrain generally operators are
comfortable to have as few as five unique segments, while
other require as many as twenty segments to satisfy their datadriven marketing needs. The decision of how many customer
segments a company should create is largely dictated by the
particular make-up of their customer base and the
organizations ability to develop and deliver unique segment
specific marketing treatments.
Fig.1 Data flow from Network Elements to IS downstream systems
III. Prepare the data for clustering
2. I found a set of valuable information to identify core needs of
subscribers based on their call detail record instead of their
personal information such as gender, address and income. A
Call Detail/Data Record contains at a minimum the following:
The number making the call (A number)
The number receiving the call (B number)
When the call started (date and time)
How long the call was (duration)
Call Type :
o
o
o
o
Voice call
SMS
Data (content)
GPRS/MMS
Balance before & after.
Location of mobile generator & terminator.
Incoming and outgoing Voice
Incoming and outgoing SMS
Different type of content
In addition to CDR we also should consider subscribers
interest to active or change any service by capturing their
action via analyzing Event Detail Records. By getting CDRs
from different sources, we would be able to make sure that
customers’ behavior captured and we can evaluate what they
are interested more and less. Any call or event from network
elements such as IN / CCN and MSC will pass through ODS
via mediation (Fig.1 shows the principle of data flow from
N.Es to IS downstream systems ) , so by accessing to the pull
of xDRs and defining proper characters ,we build our model of
customer segmentation based on their call/event detailed
record.
Considering the bellow steps (as illustrated in the Fig.2,) we
need enterprise hardware and software environment to deal
with huge amount of data (generated CDRs & EDRs) but we
also can consider sample of data to evaluate customer habits
and behaviors. Many segmentation algorithms and software
applications such as SAS and SPSS are already developed but
the most important is to follow bellow steps:
The number of data in GSM is a barrier to analysis
customer‘s behavior, so almost there is a limitation to
analysis the whole data.
CDRs & EDRs collected (by push or pull mechanism
into a data warehouse)
Different services selected:
o GPRS / MMS
o SMS
o Content e.g. RBT, Wallpaper, Java
application, Push mail, Music, Clip.
o Voice
Specific factors selected as the core items to monitor
customer‘s behavior.
Apply k-means as a well-known segmentation
algorithm.
Customer segmentation as per each recognized
factors to generate a matrix of segments.
Using Segmentation output for loyalty and customer
churn application.
Fig.2 Customer Segmentation Model
IV. CASE STUDY:
A MOBILE OPERATOR’S CUSTOMERS
CLUSTERING ANALYSIS
According to CDR (call detail records) analysis of a mobile
operator, located in the Middle East that has about 35 million
mobile subscribers, in a normal day and also holiday, the trend
shows that, the SMS usage is quite more than Call. As
Customer Segmentation is the process of splitting a customer
database into distinct, meaningful, and groups, the major
parameters such as call duration, balance, call type, tariff plan
and call time needs to be considered.
As mentioned earlier in many methods number k of clusters to
construct is an input user parameter. Running an algorithm
several times leads to a sequence of clustering systems.
Selection of the number of clusters (e.g. 10, 5, and 3) before
K-means implementation is required. However to achieve the
optimum number of clusters using the data histogram (Fig.3)
will help to make a decision as a practical solution.
The majority of subscribers use to have less call duration and
only few of them have calls up to 200 seconds.
Fig.3 Call Duration vs the number of Subscribers
3. By focusing on Call Duration and using K-means with the five
numbers of clusters (Table.1.), the center of selected clusters
areas after 19 number of iteration has been changed. The
minimum distance between initial centers is 165.000 (between
5th & 3rd segments) and the maximum is 200(between 2nd &
4th segments).The final center of clusters versus initial cluster
center has been improved as resulted in Table2.As we
expected the number of cases in each cluster is not close to
each other. According to call duration histogram, the people
who their call duration (15085 cases in 5th segment) is quite
short are more than the others.
In addition to call duration exercise, the same practice is
applicable on the other CDRs parameters such as balance
before / after, SMS, MMS, GPRS usage and other content
based parameter for customer segmentation purpose.
Furthermore, it’s highly suggested to have a matrix of major
parameters to come up with a unique plan instead of each
individual service segments.
Final Cluster Centers
Cluster
1
CALL_DURATION
2
3
4
5
421
139
59
257
10
Initial Cluster Centers
Cluster
1
CALL_DURATION
2
3
4
5
722
337
166
537
1
Distances between Final Cluster Centers
Cluster
1
1
2
3
Iteration
1
2
3
4
5
1
.000
19.596
28.955
43.135
15.805
2
51.500
27.633
12.061
30.882
.747
3
28.833
19.922
9.615
25.645
.756
4
53.381
16.630
7.859
20.455
.638
5
30.357
13.194
6.555
19.908
.565
6
22.833
11.932
5.573
19.376
.540
7
20.995
9.350
4.950
16.043
.562
8
14.232
8.933
4.130
13.544
.458
9
11.224
9.720
3.325
14.647
.344
10
14.287
8.156
3.379
12.287
.381
11
7.786
7.666
2.777
10.875
.324
12
5.498
7.140
2.288
6.635
.174
13
7.047
8.058
3.272
8.796
.350
14
11.129
7.275
2.209
10.422
.178
15
8.958
6.040
2.922
7.709
.342
16
6.050
5.457
1.844
7.140
.163
17
5.223
4.057
1.790
5.896
.230
18
.633
3.315
1.584
3.267
.211
Table.1 implementation of K-means (k=5) for call duration
282.059
3
Change in Cluster Centers
5
282.059 361.953 163.896 411.675
2
Iteration History
4
79.894
361.953
79.894
4
163.896
118.163 198.057
5
411.675
129.616 49.722
118.163 129.616
198.057 49.722
247.779
247.779
Table.2 Initial, Final and Distance between Cluster Centers
V. Customer type definition:
According to the definition of customer’s behaviors and due to
the behavior of subscribers it’s clearly shows where they are.
o Plain Loyal:
A customer that has always been Active (never went into
Dormancy or Churn status).
o Not Dependable:
A customer has reached the Churn status for the first time. He
may in the future either stay in Churn status or return to
Active (he will then be labeled ‘Loyal under Incentive’ from
now on until he reaches again and for good the Churn status).
o Fence Seated:
A customer has moved out of Active into Dormancy for the
first time. She/he may either fall into the Churn status, remain
Dormant, are become Active again.
o Loyal under Incentive:
A customer that has moved (once or several time) out of
Dormancy or Churn and back into Active status.
Based on the level of loyalty of customers during their life
cycle (Fig.3) we really need to keep the plain loyal motivated
and also provide proper motivation and package to improve
their loyalty.
4. o
o
o
o
Fig.3 Customer Life Cycle
In order to get a full picture of customer behavior in the
network and to realize their interest and also to predict their
behavior based on historical call detail record, we will analysis
mentioned scenarios in detail to identify
o
o
Which segment he/she falls into and what are the
characteristics of this segment including revenue value to
the business.
What is the risk of this customer to leave the network or
remain inactive
VI. Customers’ Behavioral Evolution
During their Life Cycle:
Based on six month historical data from enterprise data
warehouse, the statistics report of customers life cycle shows
(Fig.4) that more than 50 percent of plain loyal subscribers are
significantly decreasing while the other there type of
subscribers are not in the same level or even increasing such
as loyal under incentive subscribers.
I would like to highlight that due to behavior of subscribers
during the selected period of customers’ life cycle, we can
predict that both loyal plain and loyal under incentive
subscribers will reach to a single point. In this situation the
two various segments will merge to a unique group with
population of 40 present of total subscribers.
The volume of subscribers (Fig.4) shows that the operator is
quite a bit in a safe side at this stage; however the monitoring
of customers behavior illustrated that we will face high rate of
changes in near future.
All the subscribers are active in the network till their status
will be changed to dormant and churned status. As soon as
they become a dormant subscriber, the risk will be remained to
leave the network and churn. The highest challenge is related
to the fence seated group because they have potential capacity
to change their status into loyal incentive in a very optimistic
view or they will leave the network for ever (pessimistic).
Besides the total number of subscribers in each segment, we
need to more focus on the detailed information and track the
dynamic behavior of subscribers in each group and find a
proper answer for the following questions:
What happened to the ‘Fence Seated’ customers?
(7% of base)
What happened to the ‘Not Dependable’ customers?
(16% of base)
What happened to the ‘Loyal’ customers? (57% of
base)
Where do each ‘’Loyalty type’ sit and what strategy
to apply?
Distinguish between groups, is the key milestone to make
distinguish promotion and motivation for each individual
groups. By the same way, marketing managements can design
more suitable marketing strategy.
The behavior of Fence seated subscribers shows that all the
existing promotions and various tariff plan have not any
impact on this group, so as per detailed graph (Fig.5) after one
month only 41% of this subscribers remained in the same
situation while the 60% divided into two equal parts and joint
into “Not dependable” and “ Loyal under inventive” groups.
It’s so interesting that the after about four month the loyal
under incentive (66%) group members increased to double
compare to the Not dependable (33.5%) group members.
By focusing on not dependable subscribers which are 16% of
total subscribers, it’s illustrated that only 10% of these people
moved to loyal under incentive while the rate of movement
increased up to 37% after four month. I would like to highlight
that not dependable staff only moved to loyal under incentive
group and not to any other group. this is a good message to
keep continue and boos the existing marketing plan to increase
the number of loyal under incentive staff at the first step.
The goal is to make a plan to have specific motivation to move
three segments into the plain loyal group. The selected period
of subscribers’ life cycle is totally in a green status as more
than half out of total subscribers is plain total. There is a big
risk of churning to other operators because during the last six
month the trend of loyal subscribers is not fluctuated and
decreased to 49% that shows 8 % drop down to other groups.
Besides not dependable and fence seated groups, the two other
loyal groups have high rate of upward (Loyal under Incentive
from 19% to 33%) and downward (Plain Loyal from 57% to
49%) changes.
Fig.4 Customer Life Cycle
5. VII. Where do each ‘’Loyalty Type’ sit
What strategy to apply?
Any operator required to build strong, profitable customer
relationships with solutions that increase average revenue per
user, reduce subscriber churn and enhance brand loyalty.
In order to utilize the best criteria, two important parameters
selected to identify level of loyalty based on monthly recharge
and active on net (AON) for each segment of subscribers.
The propagation of subscribers and the location of each
loyalty type will lead the business to make an adequate plan,
so based on two mentioned items we mapped (Fig.6) four
loyalty groups into a matrix of duration (10 to 16 month) and
recharge (from 60$ to 100$) monthly basis. The margin for
AON is 13month and the recharge is 80$ monthly basis. It
means that if a subscriber is active more that 13 month on
network, then its ether plain or under incentive loyal
subscribers depend on the volume of recharge per month.
By the same way if they are less that 13 month active on
network then they are either fence seated or Not dependent ,
so it shows that we need development plan to keep them more
active on net by offering new packages as motivations.
As mentioned the boundary for monthly revenue is 80$, so it’s
quite important that even the subscribers who charge more
than specified range (80$) they are not loyal.
In addition to mentioned parameters to identify behaviors and
level of loyalty, we need to consider the service usage and also
the dependency or relation between services as part of cross
functional management to improve customer segmentation.
After we recognized the location of loyal subscribers, it’s time
to plan the right strategy for each specific segment.
The size and the status of each loyal group have been
illustrated in the Fig.6 based on their monthly recharge and
active time on the network. Both fence seated and not
dependable subscribers have less size than other two groups
and they stayed around 12 month on the network as an active
subscriber, while fence seated staff pied more than boundary.
On the other hand, two plain and under incentive loyal groups
are almost 15 month active on the net with different monthly
recharge payment. It’s clearly advised to motivate the loyal
under incentive subscribers to buy more vouchers (for
prepaid) or bill payment (postpaid) as the right strategy to
make then plain loyal as they are 33% of all subscribers.
As a general concern and risk, we might loss the entire 14% of
not dependable subscribers if they refuse to do payment.
By considering the size of each loyal group , the average
revenue per user and the location of group in the matrix
(Fig.6) , at least we would be able to initiated a strategic plan
because sometime it’s very costly to motivate this group than
put more effort and cost on the loyal under incentive or fence
seated groups to make them plain loyal on the network, so
depend on the constraints such as budget , priority and the
number of subscribers in each group, management will be able
to make a decision accordingly.
Fig.5 Detailed Behavior of Customer Life Cycle
6. XI. REFERENCES
[01] Ngai, E.W.T., Xiu, Li., Chau, D.C.K. (2008).
“Application of Data Mining Techniques in Customer
Relationship
Management.”
Expert
Systems
with
Applications, No.8:003-124.
[02] Kim, Su-Yeon. , Jung, Tae-Soo. , Suh, Eui-Ho., Hwang,
Hyun-Seok. (2006).“Customer segmentation and strategy
development based on customer lifetime value.” Expert
Systems with Applications, Vol.31:101–107.
Fig.6 Loyalty type subscribers based on their monthly recharge and active on
net duration every month
VIII. CONCLUSION
The mobile telecommunication marketplace is highly
competitive. The operators often need to design
distinguishable marketing strategy based on different behavior
of their mobile subscribers in order to improve their marketing
result and revenue. Call Detail Records describe customer
utilization behavior. They have more information to describe
customer behavior than billing system data. Clustering
analysis based on call detail records can give more
information than other clustering analysis for marketing
management. We suggested a customer life cycle model
considering the past contribution, potential value, and churn
probability at the same time. The model used for customer
segmentation. Three perspectives on customer value (current
value, potential value, and customer loyalty) assist marketing
managers in identifying customer’s segmentation with more
balanced viewpoints. After identification of subscriber’s
behavior and identification of loyal groups, it’s feasible and
possible to put mobile customer clusters in place and make an
applicable strategic plan for each group to achieve customer
satisfaction.
IX. ACKNOWLEDGMENT
The author would like to thank Dr. Gholamian for his support
in the direction of the thesis in Shiraz University. During
working on it, I got a lot of help from both supervisor and
colleagues within MTN Iran. My supervisor always tracks the
work to make sure there is no problem, and if there is, he
would give immediate help to solve the problem. And he also
gave me a good idea on how to write the thesis and what is the
process. Thanks to my colleagues, they gave me lots of
encouragement and help on both studies and work. Thanks to
my wife, she always let me know she love me which gave me
motivation. At last, I want to thank this program for the
opportunity to grow and share knowledge.
[03] So Young, Sohn. Kim, Yoonseong. (2008). “Searching
customer patterns of mobile service using clustering and
quantitative association rule.” Expert Systems with
Applications, Vol.34:1070–1077.
[04] McCarty, John A., Hastak, Manoj. (2008). “Segmentation
approaches in data-mining: A comparison of RFM, CHAID,
and logistic regression.“Journal of Business Research, Vol.60,
No. 6:656-662.
[05] Hung, Shin-Yuan. , Yen, David C., Wang, Hsiu-Yu.
(2008). “Applying data mining to telecom churn
management.”Expert Systems with Applications, Vol.31:515–
524.
[06] Charles Dennis, David Marsland, Tony Cockett. (2001).
“Data mining for shopping centers - Customer knowledge
management
framework.”
Journal
of
Knowledge
Management, Vol.5, No.4:368-374.
[07] Leea, Jang Hee., Park, Sang Chan. (2005).”Intelligent
profitable customer segmentation system based on business
intelligence tools.” Expert Systems with Applications,
Vol.29:145–152.
[08] Jain, D., & Singh, S. S. (2002).”Customer lifetime value
research in marketing: a review and future directions.”Journal
of Interactive
Marketing, Vol.16, No.2, 34–45.
[09] Mali, K. (2003).“Clustering and its validation in a
symbolic framework.” Expert Systems with Applications, Vol.
24:2367-2376.
[10] Han, J., Kamber, M. (2006), Data mining: Concepts and
Techniques, USA, Morgan Kaufmann Publishers.