1. This document contains information and data that AAUM considers confidential. Any disclosure of Confidential Information to, or use of it by any
other party, will be damaging to AAUM. Ownership of all Confidential Information, no matter in what media it resides, remains with AAUM.
AAUM Confidential
Analytics for
Telecom
2. Corporate profile
Founded by IIT Madras alumnus having extensive global business experience with Fortune 100 companies in United
States and India having three lines of business
Prof Prakash Sai
Dr. Prakash Sai is professor at the Department
of Management Studies, Indian Institute of
Technology Madras. He has wealth of
international consulting experience in Strategy
Formulation
Puneet Gupta
Puneet spearheads the IFMR Mezzanine
Finance (Mezz Co.), is strengthening the
delivery of financial services to rural households
and urban poor by making investments in local
financial institutions.
Padma Shri Dr. Ashok Jhunjhunwala
Dr. Ashok Jhunjhunwala is Professor at the
Department of Electrical Engineering, Indian
Institute of Technology Madras India. He holds a
B.Tech degree from IIT, Kanpur, and M.S. and
Ph.D degrees from the University of Maine, USA.
Analytics
• Appropriate statistical models
through which clients can measure
and grow their business.
Competitive Intelligence
• Actionable insights to clients for
their business excellence
Livelihood
•Services ranging from promotion of
livelihoods, implementation services,
livelihood & feasibility studies.
Key Focus Areas in Advanced analytics and Predictive analytics
Product – geniSIGHTS (Analytics/BI), Ordo-ab-Chao (Social Media)
More than 25 consulting assignments for Businesses & Govt orgs
Partnership – Actuate, IIT Madras, TIE and 3 strategic partnerships
Dedicated corporate office at IIT Madras Research park since 2009
Aaum’s office, IIT Madras Research Park
3. - 3 -
Competencies in
Advanced analytics
Build appropriate statistical models through
which clients can measure and grow their
business.
Expertise in
• Digital Media
• Finance/Insurance
• Travel & Logistics
• Retail
• Entertainment
• Human Capital
• Government organizations
• Research & training
Competitive
assessment
Competitive intelligence
Provide actionable insights to clients for
their business excellence.
Expertise in
• Business Entry
• Business Expansion
• Market research
Livelihood
Perform livelihood services ranging from
promotion of livelihoods, implementation
services, livelihood and feasibility studies.
Expertise in
• Government organizations
• Non Government organizations
• Corporate with livelihood focus
• Research
4. - 4 -
Relevant Solutions
for
Telecom
Analytical Advantage Using Mathematical modeling
5. - 5 -
AAUM’s capability in analytics stems from expertise to extract insights from data sources with the
ability to develop advanced mathematical models aided by experience in using statistical tools
Data sources
Business
Rules
formulation
Analytical
model development
Analytical Advantage Using Mathematical modeling
Secondary
research
Client
Primary
research
Census
Research
firms
Statistical Tools
R (Statistical
System)
WEKA (Machine
learning software)
SPSS (Multivariate
Statistical Analysis)
SAS (Data mining,
Statistical, and
Econometric
modeling)
Analytical Advantage
Profiling &
Segmentation
Product
/Process
performance
Product
/process
innovation
Valuation,
Loyalty & life
time
Market Intelligence | Finance | Retail | Telecom | Supply Chain | Consulting
Client
6. - 6 -
Our Telecom services include
Complaints
Analytics
Segmentation
Demand
Forecasting
Collection
analytics
Performance
Analytics
Pricing Analytics
Cross and Up
Selling
Churn Analytics
Telecom offerings
7. - 7 -
Churn analytics
Methodologies :
Logistic regression
Lift Curve
Data required:
Customer database for past few years.
The data could consist only of personal
customer information.
Click for Demo
8. - 8 -
Click for
Cross selling / up selling
Methodologies:
Cross/Up Sell Model Data mart
Market basket analysis predictive
model.
Data required:
• Customer, Contract, Account, Services,
Plan data
• Call detail records (CDR‟s) for pre-paid
and post-paid customers
• Disconnection, Credit, Payment
information (current and historical)
Demo
9. - 9 -
Pricing Analytics
Methodologies:
Price plan performance analytics
Rate Plan vs. Revenue Impact analytics.
Data required:
Price of all the products vs competitors
price data
DemoClick for
10. - 10 -
Complaints Analytics
Methodologies:
Segregating the complaints data on a common
taxonomy, based on a standard lexicon of definitions
of terminology and types of complaints.
Qualifying the data by severity of problem,
periodicity of occurrence, type of fault detected, etc
Statistical analysis across parameters and derive
intelligent insights from the data either as predictive
models, or as behaviour model or segment the data
into intelligent patterns
The algorithm identifies new issues in the field and
flags higher-than-normal rate faults and notifies the
appropriate analyst to let them know there is a
problem that needs investigating.
Data required:
Customer care complaints database.
Complaints on the products.
11. - 11 -
Text mining for call logs data – Frequency , similarity, clustering,
association rules to reveal text patterns
Frequently occurring terms are sent, helpdesk, etc.
Frequent terms used in the database
Clustering of call
logs on the bag of
words used
12. - 12 -
Text mining for call logs data – Lexicon based approach and advanced
machine learning algorithms for sentiment mining
Lexicon based commentometer to qualify the positivity
and negativity in choice of words
negative neutral
negative 4 0
neutral 6 30
True clustering of the
comments – SVM method
Algorithm
driven
clustering
of the
comments
Accuracy level
of 85% from
SVM method.
Advanced
analytical
algorithms for
sentiment mining
13. - 13 -
Performance analytics
Methodologies
In order to better analyze the
performance, one needs to ensure
following steps are followed.
Gathering data
Analyzing data
Presenting information in a meaningful
way
Data required:
Sales ratio data
DemoClick for
14. - 14 -
Segmentation analytics
Methodologies:
Customer Segmentation for Trend Monitoring
and Forecasting
Customer segmentation using decision tree
Marketing Response Analysis with Gains & Profit
Charts
Data required:
Geographic variables
Psychographic segmentation variables
Behavioral segmentation variables
Past business history, Customers' past business
track records
DemoClick for
15. - 15 -
Collection analytics
Methodology:
Market basket analysis
Data required:
Customer, Contract, Account, Services, Plan
data
Call detail records (CDR‟s) for pre-paid and
post-paid customers
DemoClick for
16. - 16 -
Demand forecasting
Methodologies:
Methods that rely on qualitative
assessment
Methods that rely on quantitative data
Data required:
Call detail records (CDR‟s) for pre-paid
and post-paid customers
Disconnection, Credit, Payment
information (current and historical)
DemoClick for
17. - 17 -
Questions/Feedback?
Contact us
01 N, 1st floor IIT Madras Research Park, Kanagam road, Chennai – 600113
Tel :` +91 44 66469877, Fax:+91 44 66469877
Email: info@aaumanalytics.com, Skype:b.rajeshkumar
Twitter: AaumAnalytics, Web: www.aaumanalytics.com
Facebook: http://www.facebook.com/AaumAnalytics
LinkedIn: http://www.linkedin.com/company/aaum-research-and-analytics-iit-madras
About Aaum
Aaum Research and Analytics founded by IIT Madras alumnus brings in extensive global business
experience working with Fortune 100 companies in North America and Asia Pacific. Incubated at IIT
Madras Incubator ecosystem with a focus on researching and devising the sophisticated analytical
techniques to solve the pressing business needs of corporations ranging from Health Care,
Entertainment, FMCGs, finance, insurance, retail, Telecom.
Aaum’s office at IIT Madras Research Park