2. Opportunities
Focus Areas
Factors binding focus areas and
opportunities
Background
Current Situation and system Architecture
Issues of Fraud
Churn the big question and its focus
Vineeth Menon
3. Enterprise
Performance
Revenue
Optimization
Predictive
Analytics
Call Center
Analytics
Customer
Experience
Analytics
Intelligent
Campaigns
•Master Data
Management
•Information
Rationalization
Lean predictive
analysis
Customer
Analytics
Service Enablement
Analytics
Data Analytics Opportunities
Vineeth Menon
4. What is the most appropriate network
architecture?
What is the network efficiency / cost of
ownership / individual customer experience?
How can I identify lost revenue / minimise cost
of failure?
How can I identify and effectively target customer
segments?
How can I reduce time-to-market of new
promotions?
How can I measure the efficiency of my
campaigns?
How are we doing?
What should we be doing?
How are we comparing with others?
What should we measure? Who
should view it and how often?
How can I offer a consistent customer service across channels?
How can I get a consolidated, consistent, accurate and updated
view of my customers to understand their behaviours and
profitability with trust?
How customers am I losing in this
quarter?
How to retain customers?
What were the behaviour and
requirements of lost customers?
Network analytics
Enterprise Performance
Management
Single View of Customer
Intelligent Campaigns
Churn & Retention
5. • Advanced Analytics for
Loyalty, Churn Management,
and Social Network Analysis.
• Single and Complete Customer
View
• Intelligent Campaigns provides
the best marketing expenditure.
• Enterprise Performance
Management
• Network Analytics formulates
observations and derived insight
from network traffic information
and component utilisation
• Manage churn and drive customer loyalty
and Improve retention
• Differentiate campaigns
• Predict business outcomes and manage
trends as they evolve.
• Enhance your revenue
• Optimise customer experience and
consistent experience
• Understand customer usage patterns and
behavioural tendencies
• Manage network resources and investment
costs, insight to ROI on CAPEX,OPEX
investment
• Plan for the future to support & maintain
subscriber services
• Optimise service portfolio, service experience,
network investment ,managing frauds
Helps CSPsFocus Areas
Vineeth Menon
7. Large scale data in Mobile Operator Firm
Subscribers: 500 million
Subscribers’ CDR(calling data record) data
5~8TB/day in CMCC
For a branch company (> 20 million subscribers)
Voice: 100million* 1KB = 100GB/day
SMS: 100~200 million * 1KB = 100~200GB/day
Network signaling data, for a branch company (> 20 million
subscribers)
GPRS signaling data: 48GB/day for a branch companies
3G signaling data: 300GB/day for a branch companies
voice, SMS signaling data, ……
Vineeth Menon
8. • Promotions based only on their network usage
• Network management in day to day with lesser
future analysis
• Use only active call switch for triggering
promotions
• No way of analyzing and processing high volume
CDR records
• No efficient churn analyzing method
• No access to historical data
• Complex access rules not supportive
Vineeth Menon
11. Vineeth Menon
KEY AREAS of present
day Telecom analytics
Fraud Management
Churn Prediction
Service assurance
12. Detecting Subscriber Fraud . . .
High number of calls to Black Listed numbers
High Roaming charges
High Internet Usages
High number of VAS calls
Frequent Change of Address
• Pre-Subscription Check:
• Verify address and home number
• Set Credit Limits
• Check PAN number, UID against Credit Violations
• Check IMEI against Black Listed IMEI
• Check for matching names with black listed customers.
• Check for matching PIN codes.
• Check for addresses from notorious localities.
• Match subscriber usage profile with black listed subscribers :
Called numbers
Matching tower locations
Calling patterns (short calls, long calls)
Vineeth Menon
13. Detecting Recharge Voucher Fraud . . .
• Unusual top-ups
• High number of recharges in a given time-period
Detecting Pre-paid Balance Fraud . . .
• Track employees with high number of manual
balance change
• Subscribers with high balances
Vineeth Menon
17. Churn prediction
In telecom analytics. .
Case:-
The CEO of Mobtel which is having 12 million customer base , has come to Analytics
Inc. with a problem.
Over the last two years after Mobile number portability was introduced, about 20
million subscribers has become inactive or has left Mobtel( post-paid users initially ).
Vineeth Menon
18. Churn prediction is currently a relevant subject in data
mining and has been applied in the field of banking, mobile
telecommunication , life insurances and others. In fact , all
companies who are dealing with long term customers can
take advantage of churn predict ion methods.
Models such as:-
Are common choices of data miners to tackle this churn
prediction problem .
Vineeth Menon
Neural Networks
Logical regression
Decision trees
Model