SlideShare a Scribd company logo
1 of 56
!"($%, ℎ%)
$)
*
+
,
Churn Prediction in Practice
Hands-on data science meetup
Amsterdam 5 June 2018
PRACTICALITIES
18:00 – Food & Drinks
18:25 – Welcome
18:30 – Churn Prediction in Practice - by Florian Maas
19:00 – The Churn Prediction Toolbox - by Tom de Ruijter
19:30 – Hands-on
20:30 – Drinks, gezelligheid & networking
21:00 – Everybody out
Streaming
microservices
Data science in a data pipeline
7
CHURN MODELLING IN PRACTICE
VODAFONEZIGGO
FLORIAN MAAS – 05-06-2018
8
• This presentation:
- The current approach to churn prediction within VZ
- Lessons learned & challenges faced while building this model
• Second presentation:
- More complex modelling approaches
TODAY
9
• Florian Maas
• Econometrics & Management Science, specialization in
Operations Research and Quantitative Logistics
• Supply Chain Improvement Specialist at Interface
• Co-founder of Xaperi, started joint-venture with Cadran.
• Data Scientist at VodafoneZiggo since jan 1st.
• I like running, hiking, guitar, concerts, field hockey, cycling,
boxing(?), Calvin & Hobbes and capybara’s.
WHO AM I?
10
VodafoneZiggo at a glance
#1 in Cable
8,000 employees
#2 in Mobile
4m TV connections
2.5m fixed phone connections
3m broadband internet connections
5m mobile voice/internet connections
€4b revenue
Cable Network
Coverage
Mobile
Network
Coverage
7m homes passed
VodafoneZiggo Kick off
11
A Dutch company with a global scale
• €55.9bn Revenue
• 108,000 employees
• 523m mobile customers
• €20bn Revenue
• 45,000 employees
• 50.1m homes passed
VodafoneZiggo Kick off
12
What we do really matters
For our customersFor our people For society
VodafoneZiggo Introduction
13
NIELSEN’S LAW OF INTERNET BANDWIDTH
Summary: Users' bandwidth grows by 50% per
year (10% pts. less than Moore's Law for
computer speed).
14
WHO ARE WE | ADVANCED ANALYTICS
Our mission is to unlock the value hidden in our huge pile of
data and translate it into valuable insights and data driven
products for our customers, business and stakeholders using
techniques from the field of Machine Learning and Artificial
Intelligence
15
WHAT IS CHURN?
16
WHAT IS CHURN?
Churn rate (sometimes called attrition rate), in its broadest sense, is a measure of the number of individuals or items
moving out of a collective group over a specific period.
17
HOW CAN ADVANCED ANALYTICS HELP PREVENT CHURN?
Provide a better service to our customers.
• Network optimization
• Where to place new broadcasting
equipment?
• Proactive monitoring of the network.
Provide special offers to customers.
• Who is likely to churn?
• Which offer should we give to which
customer?
Understanding the churn drivers
• What drives a customer to churn?
18
• Team:
• Platform:
• Data:
• Goal: Get a working model up and running quickly and pave the way for more complex modeling
approaches.
INITIAL APPROACH
19
1. Data
exploration
2.
Feature
engineering
3.
Model
optimization
4.
Segmentati
on &
Targeting
20
B2C FIXED CHURN PROPENSITY MODEL
All Ziggo customers Machine Learning model
0.92
0.85
0.63
0.62
0.59
0.46
0.32
0.02
Ziggo contacts customers with top
churn predictions on weekly basis
with service call
Monthly output of
customer predicted
propensity to churn
…
21
22
CURRENT MODELING APPROACH
Customer id Feature 1 Feature 2 … Churned?
1 x 0.2 … 0
2 x 1 … 1
… … … … …
Binary classification
23
24
25
DATA USAGE BOARD (DUB) & GDPR
Data of customers that have left
us some time ago
Network traffic
Certain TV package
subscriptions, such as erotic or
Arabic.
Customer data (gender, age,
customer lifetime, …)
Active products
Household information bought
from external parties
Limited data on interactions
with the help desk
26
27
PRODUCT DUMMIES – INFORMATION LEAK IN MODEL?
• This variable will be considered very important by the model and the model will draw incorrect conclusions based
on this variable.
Insert presentation title via header & footer
Product
introduction
Jan 1st April 1st
May 1st
Product unavailable; dummy 0. Product available; dummy 0 or 1
28
PRODUCT DUMMIES
Insert presentation title via header & footer
Current solution:
• Only include a dummy if a product was available in the entire period.
today – one year today – ½ year today
Included in dataset
Included in dataset
Excluded from dataset
Excluded from dataset
29
CUSTOMER INTERACTIONS
• Helpdesk interaction data
• Now included in the model as follows:
30
CUSTOMER INTERACTIONS: FUTURE
Sentiment analysis on interactions:
• Sounds nice, but this has not passed the DUB yet.
• "Calls may be recorded for training and quality purposes“
31
32
DATASET
Customer id Feature 1 Feature 2 … Churned?
1 x 0.2 0
2 x 1 0
3 y 0.5 0
4 y 0.3 1
5 z 0.2 1
6 z 0.1 0
Customer id Feature 1 Feature 2 … Churned?
1 x 0.2 0
2 x 1 0
Customer id Feature 1 Feature 2 … Churned?
3 y 0.5 0
4 y 0.3 1
Customer id Feature 1 Feature 2 … Churned?
5 z 0.2 1
6 z 0.1 0
Customer id Feature 1 Feature 2 … Churned?
1 x 0.2 0
2 x 1 0
3 y 0.5 0
4 y 0.3 1
Customer id Feature 1 Feature 2 … Churned?
5 z 0.2 1
6 z 0.1 0
Customer id Prediction
5 0.05
6 0.25
33
Customer id Feature 1 Lifetime Months in
future
6 b 10 0
6 b 11 1
6 b 12 2
Customer id Feature 1 Lifetime
6 b 10
Customer id Feature 1 Lifetime Months in
future
Prediction
6 b 10 0 0.0
6 b 11 1 0.0
6 b 12 2 0.7
Customer id Prediction
6 0.7
34
PERFORMANCE
35
MORE IMPROVEMENTS FOR THE FUTURE
• Better predictors: CSQ, 2020 errors, …
Predict which retention offer to give to which customer.
Make better use of the temporal component in the modelling of this problem.
1
3
4
Predict which customers to target, rather than predicting which customers are most likely to
churn.
2
37
!"($%, ℎ%)
$)
*
+
,
Machine learning toolbox
for churn prediction
by
Tom de Ruijter
Amsterdam 5 June 2018
Tom de Ruijter
Churn models don’t add
value
by themselves
Agenda
1. Churn: what, why and how?
2. Machine learning for churn prediction
3. Use case: churn classification at VodafoneZiggo
Agenda
1. Churn: what, why and how?
2. Machine learning for churn prediction
3. Use case: churn classification at VodafoneZiggo
What is churn?
Why does it happen?
%
PULL
PUSH
What happens?
NON-
CONTRACTUAL
CONTRACTUAL CANCELLATION
CHURN PREDICTION
Churn prevention
customer
Prevention
strategy
Churn probability
Value estimation
!(#)
%(#) Take action
Customer
contact
ORGANISATION
ALIGNMENT
ANALYTICS
EXPERIMENTAL
MINDSET
Agenda
1. Churn: what, why and how?
2. Machine learning for churn prediction
3. Use case: churn classification at VodafoneZiggo
Capturing customer life cycle into features
time
CHURN
Prediction window
Calls for time-series prediction
PROBLEM: we know very little about customers
Capturing customer life cycle into features
PULL PUSH
Competing products
Campaign history
Market presence
Spending behavior
Customer loyalty
Client interaction
Product usage
Device logs
Event logs
Customer loyalty
System design
Churn prediction algorithmcustomer data
!(#)
output
static time-series Churn in x days? Probability on time
Churn prediction algorithm
!(#)
Business rules simple, explainable > baseline
Classification model
churn in the next N days? Y/N
pre-defined window size
Probability estimation
can use censored data
flexible predictions
Client data Model Output
∑ > 3?
Baseline: business rules
=activity
=inactivity
Take action
A simple linear model
one-hot
encoded
categorical
features
…
output
!"#
$#%numerical
features
&#%
Sequence representations
timeline
Campaign
!" #$, ℎ$
call center contacted? days since last product use
#$'
!" #$, ℎ$
#$(
!" #$, ℎ$
#$)
*1 *2 *3
representation
vector
other inputs
…
Recurrent neural network architecture
sequence representation
sequence
inputs
Agenda
1. Churn: what, why and how?
2. Machine learning for churn prediction
3. Hands-on: churn classification at VodafoneZiggo
HANDS-ON WITH GOOGLE COLAB
1. Find a partner and go to: https://goo.gl/8hHbMt
2. Open with Colaboratory 3. File > Save a copy in Drive…
THANK YOU
Keep an eye on the Meetup page for the next events.

More Related Content

What's hot

Customer churn prediction for telecom data set.
Customer churn prediction for telecom data set.Customer churn prediction for telecom data set.
Customer churn prediction for telecom data set.Kuldeep Mahani
 
A case study on churn analysis1
A case study on churn analysis1A case study on churn analysis1
A case study on churn analysis1Amit Kumar
 
Churn Analysis in Telecom Industry
Churn Analysis in Telecom IndustryChurn Analysis in Telecom Industry
Churn Analysis in Telecom IndustrySatyam Barsaiyan
 
MIS637_Final_Project_Rahul_Bhatia
MIS637_Final_Project_Rahul_BhatiaMIS637_Final_Project_Rahul_Bhatia
MIS637_Final_Project_Rahul_BhatiaRahul Bhatia
 
Predicting Bank Customer Churn Using Classification
Predicting Bank Customer Churn Using ClassificationPredicting Bank Customer Churn Using Classification
Predicting Bank Customer Churn Using ClassificationVishva Abeyrathne
 
Customer attrition and churn modeling
Customer attrition and churn modelingCustomer attrition and churn modeling
Customer attrition and churn modelingMariya Korsakova
 
Telecom Churn Prediction Presentation
Telecom Churn Prediction PresentationTelecom Churn Prediction Presentation
Telecom Churn Prediction PresentationPinintiHarishReddy
 
Churn prediction
Churn predictionChurn prediction
Churn predictionGigi Lino
 
Data analytics telecom churn final ppt
Data analytics telecom churn final ppt Data analytics telecom churn final ppt
Data analytics telecom churn final ppt Gunvansh Khanna
 
Customer Churn Prevention Powerpoint Presentation Slides
Customer Churn Prevention Powerpoint Presentation SlidesCustomer Churn Prevention Powerpoint Presentation Slides
Customer Churn Prevention Powerpoint Presentation SlidesSlideTeam
 
Prediction of customer propensity to churn - Telecom Industry
Prediction of customer propensity to churn - Telecom IndustryPrediction of customer propensity to churn - Telecom Industry
Prediction of customer propensity to churn - Telecom IndustryPranov Mishra
 
Customer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in TelecomCustomer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in TelecomChris Chen
 
Data Science Use cases in Banking
Data Science Use cases in BankingData Science Use cases in Banking
Data Science Use cases in BankingArul Bharathi
 
Customer Churn Management For Profit Maximization PowerPoint Presentation Slides
Customer Churn Management For Profit Maximization PowerPoint Presentation SlidesCustomer Churn Management For Profit Maximization PowerPoint Presentation Slides
Customer Churn Management For Profit Maximization PowerPoint Presentation SlidesSlideTeam
 
Ways to Reduce the Customer Churn Rate
Ways to Reduce the Customer Churn RateWays to Reduce the Customer Churn Rate
Ways to Reduce the Customer Churn RateFORMCEPT
 

What's hot (20)

Customer churn prediction for telecom data set.
Customer churn prediction for telecom data set.Customer churn prediction for telecom data set.
Customer churn prediction for telecom data set.
 
A case study on churn analysis1
A case study on churn analysis1A case study on churn analysis1
A case study on churn analysis1
 
Churn Analysis in Telecom Industry
Churn Analysis in Telecom IndustryChurn Analysis in Telecom Industry
Churn Analysis in Telecom Industry
 
MIS637_Final_Project_Rahul_Bhatia
MIS637_Final_Project_Rahul_BhatiaMIS637_Final_Project_Rahul_Bhatia
MIS637_Final_Project_Rahul_Bhatia
 
Predicting Bank Customer Churn Using Classification
Predicting Bank Customer Churn Using ClassificationPredicting Bank Customer Churn Using Classification
Predicting Bank Customer Churn Using Classification
 
Customer attrition and churn modeling
Customer attrition and churn modelingCustomer attrition and churn modeling
Customer attrition and churn modeling
 
Telecom Churn Prediction Presentation
Telecom Churn Prediction PresentationTelecom Churn Prediction Presentation
Telecom Churn Prediction Presentation
 
Telecom Churn Prediction
Telecom Churn PredictionTelecom Churn Prediction
Telecom Churn Prediction
 
Churn prediction
Churn predictionChurn prediction
Churn prediction
 
Predicting the e-commerce churn
Predicting the e-commerce churnPredicting the e-commerce churn
Predicting the e-commerce churn
 
Data analytics telecom churn final ppt
Data analytics telecom churn final ppt Data analytics telecom churn final ppt
Data analytics telecom churn final ppt
 
Customer Churn Prevention Powerpoint Presentation Slides
Customer Churn Prevention Powerpoint Presentation SlidesCustomer Churn Prevention Powerpoint Presentation Slides
Customer Churn Prevention Powerpoint Presentation Slides
 
Telcom churn .pptx
Telcom churn .pptxTelcom churn .pptx
Telcom churn .pptx
 
Prediction of customer propensity to churn - Telecom Industry
Prediction of customer propensity to churn - Telecom IndustryPrediction of customer propensity to churn - Telecom Industry
Prediction of customer propensity to churn - Telecom Industry
 
Customer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in TelecomCustomer Churn, A Data Science Use Case in Telecom
Customer Churn, A Data Science Use Case in Telecom
 
Customer churn prediction in banking
Customer churn prediction in bankingCustomer churn prediction in banking
Customer churn prediction in banking
 
Telecom customer churn prediction
Telecom customer churn predictionTelecom customer churn prediction
Telecom customer churn prediction
 
Data Science Use cases in Banking
Data Science Use cases in BankingData Science Use cases in Banking
Data Science Use cases in Banking
 
Customer Churn Management For Profit Maximization PowerPoint Presentation Slides
Customer Churn Management For Profit Maximization PowerPoint Presentation SlidesCustomer Churn Management For Profit Maximization PowerPoint Presentation Slides
Customer Churn Management For Profit Maximization PowerPoint Presentation Slides
 
Ways to Reduce the Customer Churn Rate
Ways to Reduce the Customer Churn RateWays to Reduce the Customer Churn Rate
Ways to Reduce the Customer Churn Rate
 

Similar to Churn Prediction in Practice

Intelligent Automation 2019
Intelligent Automation 2019Intelligent Automation 2019
Intelligent Automation 2019Ray Bugg
 
Being a digital communication superstar
Being a digital communication superstarBeing a digital communication superstar
Being a digital communication superstarRon McFarland
 
Why many data science projects fail
Why many data science projects fail Why many data science projects fail
Why many data science projects fail Omnia Safaan
 
Finding the right digital tools for your internal communication strategy
Finding the right digital tools for your internal communication strategyFinding the right digital tools for your internal communication strategy
Finding the right digital tools for your internal communication strategyStephan Schillerwein
 
Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk...
 Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk... Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk...
Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk...TEST Huddle
 
2014 Future of Cloud Computing - 4th Annual Survey Results
2014 Future of Cloud Computing - 4th Annual Survey Results2014 Future of Cloud Computing - 4th Annual Survey Results
2014 Future of Cloud Computing - 4th Annual Survey ResultsMichael Skok
 
The case for 3D printing in the Always-On supply chain
The case for 3D printing in the Always-On supply chainThe case for 3D printing in the Always-On supply chain
The case for 3D printing in the Always-On supply chainMarc-Andre Leger
 
2014 Future of Cloud Computing Study
2014 Future of Cloud Computing Study2014 Future of Cloud Computing Study
2014 Future of Cloud Computing StudyNorth Bridge
 
Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!Matt Dusig
 
Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!Matt Dusig
 
Machine Learning and Industrie 4.0
Machine Learning and Industrie 4.0Machine Learning and Industrie 4.0
Machine Learning and Industrie 4.0Peter Schleinitz
 
DMA Digital Futures
DMA Digital FuturesDMA Digital Futures
DMA Digital Futuresequimedia
 
The Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine LearninThe Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine LearninInside Analysis
 
3D Printing drives the «Always-on» Supply Chain
3D Printing drives the «Always-on» Supply Chain3D Printing drives the «Always-on» Supply Chain
3D Printing drives the «Always-on» Supply ChainMarc-Andre Leger
 
Aiimi Insurance Breakfast Briefing
Aiimi Insurance Breakfast BriefingAiimi Insurance Breakfast Briefing
Aiimi Insurance Breakfast BriefingAiimiLtd
 
Business Intelligence, Data Analytics, and AI
Business Intelligence, Data Analytics, and AIBusiness Intelligence, Data Analytics, and AI
Business Intelligence, Data Analytics, and AIJohnny Jepp
 

Similar to Churn Prediction in Practice (20)

Intelligent Automation 2019
Intelligent Automation 2019Intelligent Automation 2019
Intelligent Automation 2019
 
Being a digital communication superstar
Being a digital communication superstarBeing a digital communication superstar
Being a digital communication superstar
 
3D Printing and Entrepreneurship A Co-Evolution
3D Printing and Entrepreneurship A Co-Evolution3D Printing and Entrepreneurship A Co-Evolution
3D Printing and Entrepreneurship A Co-Evolution
 
Why many data science projects fail
Why many data science projects fail Why many data science projects fail
Why many data science projects fail
 
Finding the right digital tools for your internal communication strategy
Finding the right digital tools for your internal communication strategyFinding the right digital tools for your internal communication strategy
Finding the right digital tools for your internal communication strategy
 
Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk...
 Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk... Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk...
Five Digital Age Trends That Will Dramatically Impact Testing And Quality Sk...
 
2014 Future of Cloud Computing - 4th Annual Survey Results
2014 Future of Cloud Computing - 4th Annual Survey Results2014 Future of Cloud Computing - 4th Annual Survey Results
2014 Future of Cloud Computing - 4th Annual Survey Results
 
The case for 3D printing in the Always-On supply chain
The case for 3D printing in the Always-On supply chainThe case for 3D printing in the Always-On supply chain
The case for 3D printing in the Always-On supply chain
 
2014 Future of Cloud Computing Study
2014 Future of Cloud Computing Study2014 Future of Cloud Computing Study
2014 Future of Cloud Computing Study
 
Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!
 
Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!Webinar: Everyone cares about sample quality but not everyone values it!
Webinar: Everyone cares about sample quality but not everyone values it!
 
Machine Learning and Industrie 4.0
Machine Learning and Industrie 4.0Machine Learning and Industrie 4.0
Machine Learning and Industrie 4.0
 
3D Printing and the Future of Supply Chains
3D Printing and the Future of Supply Chains3D Printing and the Future of Supply Chains
3D Printing and the Future of Supply Chains
 
DMA Digital Futures
DMA Digital FuturesDMA Digital Futures
DMA Digital Futures
 
Become a citizen data scientist
Become a citizen data scientistBecome a citizen data scientist
Become a citizen data scientist
 
The Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine LearninThe Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine Learnin
 
3D Printing drives the «Always-on» Supply Chain
3D Printing drives the «Always-on» Supply Chain3D Printing drives the «Always-on» Supply Chain
3D Printing drives the «Always-on» Supply Chain
 
Aiimi Insurance Breakfast Briefing
Aiimi Insurance Breakfast BriefingAiimi Insurance Breakfast Briefing
Aiimi Insurance Breakfast Briefing
 
When Persuasion Turns into Deception, Consumers Lose - Dries Cuijpers, Author...
When Persuasion Turns into Deception, Consumers Lose - Dries Cuijpers, Author...When Persuasion Turns into Deception, Consumers Lose - Dries Cuijpers, Author...
When Persuasion Turns into Deception, Consumers Lose - Dries Cuijpers, Author...
 
Business Intelligence, Data Analytics, and AI
Business Intelligence, Data Analytics, and AIBusiness Intelligence, Data Analytics, and AI
Business Intelligence, Data Analytics, and AI
 

Recently uploaded

RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...ThinkInnovation
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)jennyeacort
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
Data Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptxData Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptxFurkanTasci3
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home ServiceSapana Sha
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degreeyuu sss
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一F La
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 

Recently uploaded (20)

RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
Data Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptxData Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptx
 
Call Girls in Saket 99530🔝 56974 Escort Service
Call Girls in Saket 99530🔝 56974 Escort ServiceCall Girls in Saket 99530🔝 56974 Escort Service
Call Girls in Saket 99530🔝 56974 Escort Service
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 

Churn Prediction in Practice

  • 1. !"($%, ℎ%) $) * + , Churn Prediction in Practice Hands-on data science meetup Amsterdam 5 June 2018
  • 2. PRACTICALITIES 18:00 – Food & Drinks 18:25 – Welcome 18:30 – Churn Prediction in Practice - by Florian Maas 19:00 – The Churn Prediction Toolbox - by Tom de Ruijter 19:30 – Hands-on 20:30 – Drinks, gezelligheid & networking 21:00 – Everybody out
  • 4.
  • 5.
  • 6. 7 CHURN MODELLING IN PRACTICE VODAFONEZIGGO FLORIAN MAAS – 05-06-2018
  • 7. 8 • This presentation: - The current approach to churn prediction within VZ - Lessons learned & challenges faced while building this model • Second presentation: - More complex modelling approaches TODAY
  • 8. 9 • Florian Maas • Econometrics & Management Science, specialization in Operations Research and Quantitative Logistics • Supply Chain Improvement Specialist at Interface • Co-founder of Xaperi, started joint-venture with Cadran. • Data Scientist at VodafoneZiggo since jan 1st. • I like running, hiking, guitar, concerts, field hockey, cycling, boxing(?), Calvin & Hobbes and capybara’s. WHO AM I?
  • 9. 10 VodafoneZiggo at a glance #1 in Cable 8,000 employees #2 in Mobile 4m TV connections 2.5m fixed phone connections 3m broadband internet connections 5m mobile voice/internet connections €4b revenue Cable Network Coverage Mobile Network Coverage 7m homes passed VodafoneZiggo Kick off
  • 10. 11 A Dutch company with a global scale • €55.9bn Revenue • 108,000 employees • 523m mobile customers • €20bn Revenue • 45,000 employees • 50.1m homes passed VodafoneZiggo Kick off
  • 11. 12 What we do really matters For our customersFor our people For society VodafoneZiggo Introduction
  • 12. 13 NIELSEN’S LAW OF INTERNET BANDWIDTH Summary: Users' bandwidth grows by 50% per year (10% pts. less than Moore's Law for computer speed).
  • 13. 14 WHO ARE WE | ADVANCED ANALYTICS Our mission is to unlock the value hidden in our huge pile of data and translate it into valuable insights and data driven products for our customers, business and stakeholders using techniques from the field of Machine Learning and Artificial Intelligence
  • 15. 16 WHAT IS CHURN? Churn rate (sometimes called attrition rate), in its broadest sense, is a measure of the number of individuals or items moving out of a collective group over a specific period.
  • 16. 17 HOW CAN ADVANCED ANALYTICS HELP PREVENT CHURN? Provide a better service to our customers. • Network optimization • Where to place new broadcasting equipment? • Proactive monitoring of the network. Provide special offers to customers. • Who is likely to churn? • Which offer should we give to which customer? Understanding the churn drivers • What drives a customer to churn?
  • 17. 18 • Team: • Platform: • Data: • Goal: Get a working model up and running quickly and pave the way for more complex modeling approaches. INITIAL APPROACH
  • 19. 20 B2C FIXED CHURN PROPENSITY MODEL All Ziggo customers Machine Learning model 0.92 0.85 0.63 0.62 0.59 0.46 0.32 0.02 Ziggo contacts customers with top churn predictions on weekly basis with service call Monthly output of customer predicted propensity to churn …
  • 20. 21
  • 21. 22 CURRENT MODELING APPROACH Customer id Feature 1 Feature 2 … Churned? 1 x 0.2 … 0 2 x 1 … 1 … … … … … Binary classification
  • 22. 23
  • 23. 24
  • 24. 25 DATA USAGE BOARD (DUB) & GDPR Data of customers that have left us some time ago Network traffic Certain TV package subscriptions, such as erotic or Arabic. Customer data (gender, age, customer lifetime, …) Active products Household information bought from external parties Limited data on interactions with the help desk
  • 25. 26
  • 26. 27 PRODUCT DUMMIES – INFORMATION LEAK IN MODEL? • This variable will be considered very important by the model and the model will draw incorrect conclusions based on this variable. Insert presentation title via header & footer Product introduction Jan 1st April 1st May 1st Product unavailable; dummy 0. Product available; dummy 0 or 1
  • 27. 28 PRODUCT DUMMIES Insert presentation title via header & footer Current solution: • Only include a dummy if a product was available in the entire period. today – one year today – ½ year today Included in dataset Included in dataset Excluded from dataset Excluded from dataset
  • 28. 29 CUSTOMER INTERACTIONS • Helpdesk interaction data • Now included in the model as follows:
  • 29. 30 CUSTOMER INTERACTIONS: FUTURE Sentiment analysis on interactions: • Sounds nice, but this has not passed the DUB yet. • "Calls may be recorded for training and quality purposes“
  • 30. 31
  • 31. 32 DATASET Customer id Feature 1 Feature 2 … Churned? 1 x 0.2 0 2 x 1 0 3 y 0.5 0 4 y 0.3 1 5 z 0.2 1 6 z 0.1 0 Customer id Feature 1 Feature 2 … Churned? 1 x 0.2 0 2 x 1 0 Customer id Feature 1 Feature 2 … Churned? 3 y 0.5 0 4 y 0.3 1 Customer id Feature 1 Feature 2 … Churned? 5 z 0.2 1 6 z 0.1 0 Customer id Feature 1 Feature 2 … Churned? 1 x 0.2 0 2 x 1 0 3 y 0.5 0 4 y 0.3 1 Customer id Feature 1 Feature 2 … Churned? 5 z 0.2 1 6 z 0.1 0 Customer id Prediction 5 0.05 6 0.25
  • 32. 33 Customer id Feature 1 Lifetime Months in future 6 b 10 0 6 b 11 1 6 b 12 2 Customer id Feature 1 Lifetime 6 b 10 Customer id Feature 1 Lifetime Months in future Prediction 6 b 10 0 0.0 6 b 11 1 0.0 6 b 12 2 0.7 Customer id Prediction 6 0.7
  • 34. 35 MORE IMPROVEMENTS FOR THE FUTURE • Better predictors: CSQ, 2020 errors, … Predict which retention offer to give to which customer. Make better use of the temporal component in the modelling of this problem. 1 3 4 Predict which customers to target, rather than predicting which customers are most likely to churn. 2
  • 35. 37
  • 36. !"($%, ℎ%) $) * + , Machine learning toolbox for churn prediction by Tom de Ruijter Amsterdam 5 June 2018
  • 38. Churn models don’t add value by themselves
  • 39. Agenda 1. Churn: what, why and how? 2. Machine learning for churn prediction 3. Use case: churn classification at VodafoneZiggo
  • 40. Agenda 1. Churn: what, why and how? 2. Machine learning for churn prediction 3. Use case: churn classification at VodafoneZiggo
  • 42. Why does it happen? % PULL PUSH
  • 44. CHURN PREDICTION Churn prevention customer Prevention strategy Churn probability Value estimation !(#) %(#) Take action Customer contact ORGANISATION ALIGNMENT ANALYTICS EXPERIMENTAL MINDSET
  • 45. Agenda 1. Churn: what, why and how? 2. Machine learning for churn prediction 3. Use case: churn classification at VodafoneZiggo
  • 46. Capturing customer life cycle into features time CHURN Prediction window Calls for time-series prediction PROBLEM: we know very little about customers
  • 47. Capturing customer life cycle into features PULL PUSH Competing products Campaign history Market presence Spending behavior Customer loyalty Client interaction Product usage Device logs Event logs Customer loyalty
  • 48. System design Churn prediction algorithmcustomer data !(#) output static time-series Churn in x days? Probability on time
  • 49. Churn prediction algorithm !(#) Business rules simple, explainable > baseline Classification model churn in the next N days? Y/N pre-defined window size Probability estimation can use censored data flexible predictions
  • 50. Client data Model Output ∑ > 3? Baseline: business rules =activity =inactivity Take action
  • 51. A simple linear model one-hot encoded categorical features … output !"# $#%numerical features &#%
  • 52. Sequence representations timeline Campaign !" #$, ℎ$ call center contacted? days since last product use #$' !" #$, ℎ$ #$( !" #$, ℎ$ #$) *1 *2 *3 representation vector
  • 53. other inputs … Recurrent neural network architecture sequence representation sequence inputs
  • 54. Agenda 1. Churn: what, why and how? 2. Machine learning for churn prediction 3. Hands-on: churn classification at VodafoneZiggo
  • 55. HANDS-ON WITH GOOGLE COLAB 1. Find a partner and go to: https://goo.gl/8hHbMt 2. Open with Colaboratory 3. File > Save a copy in Drive…
  • 56. THANK YOU Keep an eye on the Meetup page for the next events.