1. Successful marketing with
Big Data Analytics
A use case from Asia
Johannes Bjelland, Pål Sundsøy
Telenor Group Research
Digital Winners, Fornebu 08.11.2013
2. Our customers generate an
increasing amount of
information in our systems
What’s in it for
Telenor?
3. For each call, sms and data session:
hundreds of data points are stored
A number - Caller
Date & time
B number –
Receiving party
Type:
Call, SMS, Data, et
c
Data volume
Cell_ID: Location
IMSI: SIM card
TAC: Handset
3
4. Boosting Mobile Internet uptake in Asia with
prediction and SMS marketing
Motivation
•
•
•
For many in Asia, the mobile phone is
their only gateway to the Web.
Many customers have internet capable
phones, but do not use them
The business unit is using state of the art
Below The Line marketing process
This Pilot was a collaboration with the Mobile Internet Asia project in Digital Services
5. Selecting the right campaign target groups is key
to maximize Campaign revenue
Customer attention is valuable and a
limited resource!
• 6000 yearly SMS campaigns effectively boost
customer revenues
• Number of campaigns cannot be pushed further
• Contact rules: Max 1 offer each 14 days
• Efficiency of campaigns can be improved with a big
data approach
5
08/11/2013
6. Machine Learning assists us in selecting optimal
target customers from huge data sets
Data sources
• Traffic usage data
• Subscription data
• Handset Features
• Location
• Handset switching
• VAS usage
300 variables
40 000 000
customers
Who are most
profitable targets
for SMS campaign
?
8. The predictive model learns from existing
cases of data conversion
Non-convertors
‘Negatives’
Create model
Find patterns
identifying the data
convertors based on
historic data
Natural Data
Convertors
‘Positives’
2-6 months back: Use Historical data
Today: Present time data
Non Data
Customers
today
Model
deployment
Use the patterns to
identify likely adopters
*Offers are 15 MB & 99 MB data packages offered for half-price
Identify and Run
Campaign on
200k most likely
adopters
9. The prediction model outperforms existing best practice
approach – 13 times better than best practice
Actual Campaign Hit Rate
Hitrate
7.00
6.42
6.00
5.00
3.76
4.00
PSPM
Prediction Model
3.00
Microsegmentation
Current best
practice
Microsegmentation
approach
2.00
1.00
0.50
0.70
0.00
P7 Package
15 MB Datadata pack
P9 data pack
99 MB Data Package
99% Renewal– the algorithm is optimized to avoid ‘freeriders’
10. Telenor Data-Driven Development
Using data for social good
Detecting signals in the data
•
Use mobile phone data to Improve models for Infectious disease spread
•
Understand the spread of Dengue fever in Pakistan
•
Collaboration with epidemiologists from Harvard School of Public Health
•
Crisis and Disaster Management
•
Assessing mobility patterns and changes in economic behavior during the Cyclone Mahasen (May 2013).
•
Goal: Improve efficiency of emergency aid measures
•
Measuring Socio-economic state based on big data
•
Collaboration to be set up between UN Global Pulse, World Food Program and Telenor Group.
•
Food security - food prices and availability
11. A ‘Big Data’ company is distinguished, not by how many
terabytes it sits on, but by the way the company exploits the
data in Business!
Telenor is taking steps toward
becoming a Big Data company
• Answering business questions via data mining
and ad hoc analysis
• Using pilots and data driven marketing to let
the customers tell us what they want
• Collaborating with world leading research
environments within data science
• Petabytes is not a prerequisite - What we
need is ‘BIG ENOUGH’ Data for business