www.decideo.fr/bruleychurn extract from various presentations: owens, telecom lab, aster data …...
Post on 23-Dec-2015
214 Views
Preview:
TRANSCRIPT
www.decideo.fr/bruley
ChurnChurn
Extract from various presentations: Owens, Telecom Lab, Aster Data …
michel.bruley@teradata.com
January 2013January 2013
www.decideo.fr/bruley
Churn in Comm. Industry: a bottom line issue
Attracting thousands of new subscribers is worthless if an equal number are leaving
Minimizing customer churn provides a number of benefits, such as:
– Minor investment in acquiring a new customer
– Higher efficiency in network usage
– Increase of added-value sales to long term customers
– Decrease of expenditure on help desk
– Decrease of exposure to frauds and bad debts
– Higher confidence of investors
www.decideo.fr/bruley
Poor Service
45%
Lack of Attention
20%
Price15%
Quality15%
Other5%
How can I effectively manage customer churn?Why are my customers churning?
How do I identify key churn drivers across the customer lifecycle?How can I predict when my customers will churn?
What kind of initiatives can I run to anticipate customer churn and address drivers of churn?How do I report on churn and retention initiatives?
Churn: Why Customers Leave
www.decideo.fr/bruley
Churn management: scoping the problem (1)
Churn can be defined and measured in different ways
– “Absolute” Churn. number of subscribers disconnected, as a percentage of the subscriber base over a given period
– “Line” or “Service” Churn. number of lines or services disconnected, as a percentage of the total amount of lines or services subscribed by the customers
– “Primary Churn”. number of defections
– “Secondary Churn”. drop in traffic volume, with respect to different typology of calls
www.decideo.fr/bruley
Churn management: scoping the problem (2)
Measuring churn is getting more and more difficult
– Growing tendency for Business users to split their business between several competing fixed network operators
– Carrier selection enables Residential customers to make different kind of calls with different operators
– Carrier pre-selection and Unbundling of the Local Loop makes it very difficult to profile customers according to their “telecommunication needs”
Other frequent questions for Fixed Network Services
– What if a customer changes his type of subscription, but remains in the same telco? What if the name of a subscriber changes? What if he relocates?
www.decideo.fr/bruley
The case: Churn Analysis for wireless services
The framework
– A major network operator willing to establish a more effective process for implementing and measuring the performance of loyalty schemes
Objectives of the “churn management” project
– Building a new corporate Customer Data Warehouse aimed to support Marketing and Customer Care areas in their initiatives
– Developing a Churn Analysis system based upon data mining technology to analyze the customer database and predict churn
www.decideo.fr/bruley
Business understanding
Sponsors
– Marketing dept., IT applications, IT operations
Analysis target
– Residential Customers, subscriptions
Churn measurement
– Absolute, primary churn
Goal:
– Predict churn/no churn situation of any particular customer given 5 months of historical data
www.decideo.fr/bruley
Solution scope
millions of residential customers
millions of customers
millions of business customers
Usage patterns analysis of Voice Services by
single subscriber line
Usage patterns analysis of Voice Services by
subscriber line, contract, company, etc.
Usage patterns analysis of VAS by single subscriber line
www.decideo.fr/bruley
Application framework
ContractsTariff plansBilling data
Accounts dataFraud / Bad debts data
Customer dataMarket dataSales data
Customer service contacts
Front-officeSystems
Marketing automation
Service automation
Salesautomation
Marketing
ListenerLoader
Loader
Loader ... ......
ETL
Data Collection &Transformation
Data Preprocessing
Data Server
Data Warehouse
Analytical Applications
Reporting OLAP
Data Mining
Decision Engine
Back-officeSystems
•Campaign Targets•New product /
services•Loyalty schemes
•Performance analysis
www.decideo.fr/bruley
Data understanding
CustomerData Warehouse
Input Data• Customer demographics
Basic customer information• Service Profile
Products/services purchased by each customer.
• Tariff plansDetails of the tariff scheme in use• Extra service information
Special plans / ratesService bundles
• Call data aggregated by month• Billing data aggregated by month
• Complaint information• Fraud and bad debts data• Customer service contacts
• Sales force contacts• Market data
xx operational systems
•More than 500 indicators per customer•Loading: on a monthly basis
•Size: xTB
www.decideo.fr/bruley
Modeling with Data Mining tool
Main steps
– Define Concepts, Attributes, Relationships …
– Select Operators
– Build the execution workflow
www.decideo.fr/bruley
Concepts, Attributes, Relationships
Demographic attributes
Call data records
Data about subscribed
services
Revenue data
www.decideo.fr/bruley
Construction stage output
16 Raw attributes
45 Derived attributes
Data Construction Feature Selection
www.decideo.fr/bruley
Churn modeling chain
Medium value customers are selected
training set
decision tree operator applied to fit predict the
likelihood of a customer to become a churner in the
month M6
Save output
4 Predictive models, one for each
customer segment
www.decideo.fr/bruley
Predictive performance
PRED_ACTPRED_CHN
ACTIVE
CHURNER
11
8986
140
20
40
60
80
100
MEDIUM customer model performance
PRED_ACTPRED_CHN
ACTIVE
CHURNER
19
8194
60
20
40
60
80
100
HIGH customer model performance
PRED_ACTPRED_CHN
ACTIVE
CHURNER
5
95
67
33
0
20
40
60
80
100
VERY LOW customer model performance
PRED_ACTPRED_CHN
ACTIVE
CHURNER
25
7582
180
20
40
60
80
100
LOW customer model performance
www.decideo.fr/bruley
What Is Graph Analysis?
Aster: MapReduce implementations for graph analysis
Operates on Any Transaction or Interaction Data
•Identifies the individuals or nodes in a network•Identifies the relationships or edges in a network
In-Memory Graph Structure Allows for Graph Analytics
•MapReduce creates a graph object that can then be traversed for analysis
•Traversal of the graph is non-trivial even for simple graph analysis
Output of Graph Analysis Is Flexible
•MapReduce used to dynamically bind structure to data on execution
www.decideo.fr/bruley
Teradata Aster Graph Analysis
Why this belongs on Aster
• Limitations in SQL Relational DBMSs- Set-based SQL is a poor programming construct
for Graph problems
- Every connection between 2 people is a self-join in SQL
• Aster Advantages- Read & transform data into in-memory graph
structure
- Perform standard SQL logic or MapReduce on the in-memory graph structure
- Influencer Analytics: traverse the graph for single shortest path – six degrees of Kevin Bacon
Aster Metrics: Social Graph Analysis
Environment:
1 billion rows, 700GB, 11 workers
Aster Response:
180 Seconds
www.decideo.fr/bruley
Graph Analysis & Churn Prediction
Graph Analysis constructs an influence propagation model
- Given persons who churned (initial churners)- Diffuse their influence into their social environment- Thus, their friends are at a larger churn risk.. (The two C1s churn; N does not) - And this propagates to some of their friends’ friends (C2 affected due to indirect, cumulative influence)
Output
- List of predicted churners
Business Value
- Captures higher order social effects - Capture the effect of multiple churners on a subscriber- Does not require profile information- Once the model is created, it can be run quickly & often - Complements traditional churn models
I
C1
*
N
*
*
I
C1
C2
I Initial churners (known)
C Predicted churners
Influence spreading
Indirect influence
www.decideo.fr/bruley
Identify most frequent paths to early termination of service
Analyze specific patterns of customer behavior
Across multiple channels of customer engagement – web,
retail, customer service
Multi-Channel Path Analysis
Understand customers paths to service Understand customers paths to service cancellationcancellation
www.decideo.fr/bruley
*nPath analysis
Propensity-to-churn model
call drop outs
data drop outs in web (PDP) sessions
level of call quality (voice and data speed)
3G to 2G drop down and length of time on 2G.
sentiment analysis from call center records
Customer experience score
Propensity to churn
Path to churn
Good Score = Upsell opportunity
Bad Score = Retention Activities
Variation Score = Explanatory Message/Action
*nPath - pre-packaged SQL-MapReduce function for finding sequences of events
Customer Journey across Multiple Customer Journey across Multiple ChannelsChannels
www.decideo.fr/bruley
Analysis across Diverse Sources & Data Analysis across Diverse Sources & Data Types Types
www.decideo.fr/bruley
Discover Specific Service Cancellation Discover Specific Service Cancellation PathsPaths
www.decideo.fr/bruley
Big Data & Churn Prevention
•Enrich Traditional Churn Model•Graph Analysis
•Multi-Channel Path Analysis
Business impact•With significantly less effort, know when customers are in the
last mile of considering leaving•Higher customer retention leading to lower costs and higher
profitability•Higher customer satisfaction
Detect & Prevent Customer Detect & Prevent Customer ChurnChurn
top related