SlideShare a Scribd company logo
Oct 27, 2018
Akanksha Tiwari
Rakuten Institute of Technology
Singapore
2
I have built a model to predict which customer will cancel their subscription
..why is marketing not using it?
1. Marketing team will not use the model if they don’t know what action to take
on the predictions and why
2. Data Scientists can use model interpretation to help marketing team take
action
Video streaming platform that
streams Asian content.
4
Customers pay monthly
subscription fee to watch
content
Customers cancel
subscription and leave
+ $ - $
CHURN
5
…
Yes, sure.
That sounds
exciting
Management
Why don't we
start using AI to
identify which
customers will
churn next
month ?
Marketing
6
…
Yes, sure.
That sounds
exciting
Management
Why don't we
start using AI to
identify which
customers will
churn next
month ?
Marketing
Can you help
identify customers
who will churn next
month?
Data Scientist
7
…
Sure. I can use
past data to build
a model to predict
who will churn in
the next month.
Data Scientist
8
…
FEATURES
Video Viewing
Behavior
Click Stream
Behavior
Subscription
Behavior
Train the model on past
subscribers
Predict the probability to
churn in the next month
Model Outperforms vendor’s model
9
…
Data Scientist
10
…
If client is unable to action on predictions then the model will not be used
How should the output of the
model be used ? Given the
high risk churners what should
I do and why?
Marketing
11
Customer Probability to churn
X 0.27
Y 0.86
Z 0.82
CHURN MODEL PREDICTIONS
12
Customer Probability to churn Reason for prediction
X 0.27 Used service for more than year, Actively watching content
Y 0.86 New User, Cancelled in the past
Z 0.82
Used service for more than year, Lost Interest
CHURN MODEL PREDICTIONS EXPLANATION
13
MODEL INTERPRETATION
Model Interpretation of a machine learning model is how humans can
understand the choices made by the model in the decision making process
MODEL PREDICTIONS EXPLANATION
14
15
*(see the SHAP NIPS paper for details).
SHAP*:
• Latest work on model interpretation
• Explains the output of any machine learning model.
• Connects game theory with model explanations
• Unifies several previous methods (such as LIME, DeepLift)
16
Member A
What is an individual’s contribution in the team?
Team makes $400 profits
Member B Member C
17
Mapping teams to model prediction (Example)
Team Members  Features used for a prediction
Team sales  Prediction Score
Member A
Member A
Member A
$400 0.78
Days since subscription
Minutes Viewed
Number of past subscriptions
18
1: Calculate Normalizing Weights for all sub-sizes of teams
Team Size Normalizing Weight* Team Permutations
1
2
3
33%
16%
33% *Normalizing Weight = m! x (n-m-1)! / n!
n = size of original team
m = size of team player get’s added to
19
2: Contribution when each member is working alone
$200 $100 $0
Member A Member B Member C
20
3: Contribution of players as part of teams
B’s contribution
(in a team with A)
= 400 - 200 = $200
A’s contribution
(in a team with B)
= 400 - 100 = $300
+ = $400
Member A Member B
21
4: Final contributions
Final SHAP AttributionsNormalizing Weights
Team of 1
$200
$100
$0
33% 16% 33%
$200 + $300
= $500
=$300
$0
$300
$200
$0
Team of 2 Team of 3
33% x $200 + 16% x $500 + 33% x $300
= $250
= $0
= $150
Member A
Member B
Member C
22
No. of past cancellations
= 5
Prediction with a high churn score
23
Explanation of the prediction of the high churn score
days since subscription = 25
Minutes viewed last
quarter
(of subscription) = 0
No. of past cancellations = 5
24
Days since subscription = 311
Minutes viewed last quarter
(of subscription) = 3751
Days since last watched video = 0
Sample explanation of a low churn score
25
Flip the horizontal predictions vertically
26
Group all predictions by their SHAP values
27
Days since subscription = 31
days
Minutes viewed last quarter = 0
New users,
not watching content
Higher
lower
S
H
A
P
V
A
L
U
E
S
USERS
Helps marketing understand the decisions of the model
28
Disengaged
users
Higher
lower
Days since subscription = 301
Drop in minutes watched > 50%
Minutes viewed last quarter = 0
USERS
S
H
A
P
V
A
L
U
E
S
Helps marketing understand the decisions of the model and take action
29
Marketing Planning a campaign for disengaged users using content recommendation
Acquisition Date: 24th Sep 2018
30
Revisit model / data
Higher
lower
Minutes viewed in 2nd quarter of subscription =
1000
Minutes viewed drop > 50 %
Minutes viewed in last quarter = 0
S
H
A
P
V
A
L
U
E
S
Helps in in Qualitative Model Evaluation
31
• Churn prediction is just one component of churn management
• Marketing will not use the model if they don’t know what action to take on the
predictions and why
• Use model interpretation to help marketing take action
Why is my machine learning  model not being used ?

More Related Content

What's hot

Deep learning for e-commerce: current status and future prospects
Deep learning for e-commerce: current status and future prospectsDeep learning for e-commerce: current status and future prospects
Deep learning for e-commerce: current status and future prospects
Rakuten Group, Inc.
 
E-commerce企業におけるビッグデータ活用の取り組みと今後の展望
E-commerce企業におけるビッグデータ活用の取り組みと今後の展望E-commerce企業におけるビッグデータ活用の取り組みと今後の展望
E-commerce企業におけるビッグデータ活用の取り組みと今後の展望
Rakuten Group, Inc.
 
940 sponsor gazdak_using our laptop
940 sponsor gazdak_using our laptop940 sponsor gazdak_using our laptop
940 sponsor gazdak_using our laptop
Rising Media, Inc.
 
Data Science Salon: Adopting Machine Learning to Drive Revenue and Market Share
Data Science Salon: Adopting Machine Learning to Drive Revenue and Market ShareData Science Salon: Adopting Machine Learning to Drive Revenue and Market Share
Data Science Salon: Adopting Machine Learning to Drive Revenue and Market Share
Formulatedby
 
Projects
ProjectsProjects
Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...
Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...
Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...
Formulatedby
 
Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...
Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...
Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...
Data Driven Innovation
 
Ai in finance
Ai in financeAi in finance
Ai in finance
QuantUniversity
 
State of MLOps 2021 valohai survey_요약정리
State of MLOps 2021 valohai survey_요약정리State of MLOps 2021 valohai survey_요약정리
State of MLOps 2021 valohai survey_요약정리
Chun Myung Kyu
 
Value of Data Science
Value of Data ScienceValue of Data Science
Value of Data Science
Akin Osman Kazakci
 
Cognitive Assistant for Data Scientists (CADS)
Cognitive Assistant for Data Scientists (CADS)Cognitive Assistant for Data Scientists (CADS)
Cognitive Assistant for Data Scientists (CADS)
Steven Miller
 
How to get on the AI journey?
How to get on the AI journey? How to get on the AI journey?
How to get on the AI journey?
Aarthi Srinivasan
 
What is data science ?
What is data science ?What is data science ?
What is data science ?
Bohitesh Misra, PMP
 
MLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business PerspectiveMLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business Perspective
BigML, Inc
 
Machine learning for broadcasting & media production
Machine learning for broadcasting & media productionMachine learning for broadcasting & media production
Machine learning for broadcasting & media production
Maxim Kublitski
 
Marketing Analytics with R Lifting Campaign Success Rates
Marketing Analytics with R Lifting Campaign Success RatesMarketing Analytics with R Lifting Campaign Success Rates
Marketing Analytics with R Lifting Campaign Success Rates
Revolution Analytics
 
Machine Learning for Sales & Marketing
Machine Learning for Sales & MarketingMachine Learning for Sales & Marketing
Machine Learning for Sales & Marketing
Piyush Saggi
 
Future of datascience
Future of datascienceFuture of datascience
Future of datascience
jyostnanareshit
 
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at BidtellectData Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
Formulatedby
 
Debugging AI
Debugging AIDebugging AI
Debugging AI
Dr. Christian Betz
 

What's hot (20)

Deep learning for e-commerce: current status and future prospects
Deep learning for e-commerce: current status and future prospectsDeep learning for e-commerce: current status and future prospects
Deep learning for e-commerce: current status and future prospects
 
E-commerce企業におけるビッグデータ活用の取り組みと今後の展望
E-commerce企業におけるビッグデータ活用の取り組みと今後の展望E-commerce企業におけるビッグデータ活用の取り組みと今後の展望
E-commerce企業におけるビッグデータ活用の取り組みと今後の展望
 
940 sponsor gazdak_using our laptop
940 sponsor gazdak_using our laptop940 sponsor gazdak_using our laptop
940 sponsor gazdak_using our laptop
 
Data Science Salon: Adopting Machine Learning to Drive Revenue and Market Share
Data Science Salon: Adopting Machine Learning to Drive Revenue and Market ShareData Science Salon: Adopting Machine Learning to Drive Revenue and Market Share
Data Science Salon: Adopting Machine Learning to Drive Revenue and Market Share
 
Projects
ProjectsProjects
Projects
 
Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...
Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...
Data Science Salon: Building smart AI: How Deep Learning Can Get You Into Dee...
 
Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...
Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...
Forecasting and Predictive Digital Marketing. Daniele Donzella, Gianluigi Spa...
 
Ai in finance
Ai in financeAi in finance
Ai in finance
 
State of MLOps 2021 valohai survey_요약정리
State of MLOps 2021 valohai survey_요약정리State of MLOps 2021 valohai survey_요약정리
State of MLOps 2021 valohai survey_요약정리
 
Value of Data Science
Value of Data ScienceValue of Data Science
Value of Data Science
 
Cognitive Assistant for Data Scientists (CADS)
Cognitive Assistant for Data Scientists (CADS)Cognitive Assistant for Data Scientists (CADS)
Cognitive Assistant for Data Scientists (CADS)
 
How to get on the AI journey?
How to get on the AI journey? How to get on the AI journey?
How to get on the AI journey?
 
What is data science ?
What is data science ?What is data science ?
What is data science ?
 
MLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business PerspectiveMLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business Perspective
 
Machine learning for broadcasting & media production
Machine learning for broadcasting & media productionMachine learning for broadcasting & media production
Machine learning for broadcasting & media production
 
Marketing Analytics with R Lifting Campaign Success Rates
Marketing Analytics with R Lifting Campaign Success RatesMarketing Analytics with R Lifting Campaign Success Rates
Marketing Analytics with R Lifting Campaign Success Rates
 
Machine Learning for Sales & Marketing
Machine Learning for Sales & MarketingMachine Learning for Sales & Marketing
Machine Learning for Sales & Marketing
 
Future of datascience
Future of datascienceFuture of datascience
Future of datascience
 
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at BidtellectData Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
 
Debugging AI
Debugging AIDebugging AI
Debugging AI
 

Similar to Why is my machine learning model not being used ?

6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...
6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...
6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...
saastr
 
Tech Leadership for the Sustainable Win
Tech Leadership for the Sustainable WinTech Leadership for the Sustainable Win
Tech Leadership for the Sustainable Win
Holly Ross
 
#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win
#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win
#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win
Connecting Up
 
SplitMetrics answers burning questions on mobile A/B testing
SplitMetrics answers burning questions on mobile A/B testingSplitMetrics answers burning questions on mobile A/B testing
SplitMetrics answers burning questions on mobile A/B testing
SplitMetrics
 
Do you know the real story your data is telling you?
Do you know the real story your data is telling you?Do you know the real story your data is telling you?
Do you know the real story your data is telling you?
4Ps Marketing
 
DMAI Analytics Solutions Guide
DMAI Analytics Solutions GuideDMAI Analytics Solutions Guide
DMAI Analytics Solutions Guide
Dan Meyer
 
What is Analytics for Your Business?
What is Analytics for Your Business?What is Analytics for Your Business?
What is Analytics for Your Business?
tricia eunice baylon
 
Funnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GAFunnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GA
Sofia Quintero
 
Product Analytics Workshop
Product Analytics WorkshopProduct Analytics Workshop
Product Analytics Workshop
Amplitude
 
Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...
Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...
Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...
Adestra
 
Microsoft adoption guide workbook
Microsoft adoption guide workbookMicrosoft adoption guide workbook
Microsoft adoption guide workbook
Kamal Pandey
 
Conversion Conference 2011 NYC presentation
Conversion Conference 2011 NYC presentationConversion Conference 2011 NYC presentation
Conversion Conference 2011 NYC presentation
Brian Jones
 
Machine Learning with Azure and Databricks Virtual Workshop
Machine Learning with Azure and Databricks Virtual WorkshopMachine Learning with Azure and Databricks Virtual Workshop
Machine Learning with Azure and Databricks Virtual Workshop
CCG
 
Learncool - Angel Round Pitch
Learncool - Angel Round Pitch Learncool - Angel Round Pitch
Learncool - Angel Round Pitch
Shishir Choudhary
 
Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0
John Grudnowski
 
Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0
John Grudnowski
 
Hero Conf London 2018 - Frameworks for Insights and Impact
Hero Conf London 2018 - Frameworks for Insights and ImpactHero Conf London 2018 - Frameworks for Insights and Impact
Hero Conf London 2018 - Frameworks for Insights and Impact
Wijnand Meijer
 
Digital Learning Blueprint Template
Digital Learning Blueprint TemplateDigital Learning Blueprint Template
Digital Learning Blueprint Template
Judy Albers
 
Minimum viable product_to_deliver_business_value_v0.4
Minimum viable product_to_deliver_business_value_v0.4Minimum viable product_to_deliver_business_value_v0.4
Minimum viable product_to_deliver_business_value_v0.4Archana Joshi
 
How to Apply Machine Learning by Lyft Senior Product Manager
How to Apply Machine Learning by Lyft Senior Product ManagerHow to Apply Machine Learning by Lyft Senior Product Manager
How to Apply Machine Learning by Lyft Senior Product Manager
Product School
 

Similar to Why is my machine learning model not being used ? (20)

6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...
6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...
6 Steps to Building the Ultimate Integrated Marketing Framework with Productb...
 
Tech Leadership for the Sustainable Win
Tech Leadership for the Sustainable WinTech Leadership for the Sustainable Win
Tech Leadership for the Sustainable Win
 
#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win
#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win
#CU11: Workshop by Holly Ross: Technology Leadership for the Sustainable Win
 
SplitMetrics answers burning questions on mobile A/B testing
SplitMetrics answers burning questions on mobile A/B testingSplitMetrics answers burning questions on mobile A/B testing
SplitMetrics answers burning questions on mobile A/B testing
 
Do you know the real story your data is telling you?
Do you know the real story your data is telling you?Do you know the real story your data is telling you?
Do you know the real story your data is telling you?
 
DMAI Analytics Solutions Guide
DMAI Analytics Solutions GuideDMAI Analytics Solutions Guide
DMAI Analytics Solutions Guide
 
What is Analytics for Your Business?
What is Analytics for Your Business?What is Analytics for Your Business?
What is Analytics for Your Business?
 
Funnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GAFunnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GA
 
Product Analytics Workshop
Product Analytics WorkshopProduct Analytics Workshop
Product Analytics Workshop
 
Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...
Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...
Keynote Presentation: Incremental Innovation in the Age of the Customer - Sim...
 
Microsoft adoption guide workbook
Microsoft adoption guide workbookMicrosoft adoption guide workbook
Microsoft adoption guide workbook
 
Conversion Conference 2011 NYC presentation
Conversion Conference 2011 NYC presentationConversion Conference 2011 NYC presentation
Conversion Conference 2011 NYC presentation
 
Machine Learning with Azure and Databricks Virtual Workshop
Machine Learning with Azure and Databricks Virtual WorkshopMachine Learning with Azure and Databricks Virtual Workshop
Machine Learning with Azure and Databricks Virtual Workshop
 
Learncool - Angel Round Pitch
Learncool - Angel Round Pitch Learncool - Angel Round Pitch
Learncool - Angel Round Pitch
 
Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0
 
Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0Display Measurement Concepting To Completion V2.0
Display Measurement Concepting To Completion V2.0
 
Hero Conf London 2018 - Frameworks for Insights and Impact
Hero Conf London 2018 - Frameworks for Insights and ImpactHero Conf London 2018 - Frameworks for Insights and Impact
Hero Conf London 2018 - Frameworks for Insights and Impact
 
Digital Learning Blueprint Template
Digital Learning Blueprint TemplateDigital Learning Blueprint Template
Digital Learning Blueprint Template
 
Minimum viable product_to_deliver_business_value_v0.4
Minimum viable product_to_deliver_business_value_v0.4Minimum viable product_to_deliver_business_value_v0.4
Minimum viable product_to_deliver_business_value_v0.4
 
How to Apply Machine Learning by Lyft Senior Product Manager
How to Apply Machine Learning by Lyft Senior Product ManagerHow to Apply Machine Learning by Lyft Senior Product Manager
How to Apply Machine Learning by Lyft Senior Product Manager
 

More from Rakuten Group, Inc.

コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
Rakuten Group, Inc.
 
楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり
Rakuten Group, Inc.
 
What Makes Software Green?
What Makes Software Green?What Makes Software Green?
What Makes Software Green?
Rakuten Group, Inc.
 
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Rakuten Group, Inc.
 
DataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組みDataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組み
Rakuten Group, Inc.
 
大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開
Rakuten Group, Inc.
 
楽天における大規模データベースの運用
楽天における大規模データベースの運用楽天における大規模データベースの運用
楽天における大規模データベースの運用
Rakuten Group, Inc.
 
楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー
Rakuten Group, Inc.
 
楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割
Rakuten Group, Inc.
 
Rakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdfRakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdf
Rakuten Group, Inc.
 
The Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdfThe Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdf
Rakuten Group, Inc.
 
Supporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdfSupporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdf
Rakuten Group, Inc.
 
Making Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdfMaking Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdf
Rakuten Group, Inc.
 
How We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdfHow We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdf
Rakuten Group, Inc.
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech info
Rakuten Group, Inc.
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech info
Rakuten Group, Inc.
 
OWASPTop10_Introduction
OWASPTop10_IntroductionOWASPTop10_Introduction
OWASPTop10_Introduction
Rakuten Group, Inc.
 
Introduction of GORA API Group technology
Introduction of GORA API Group technologyIntroduction of GORA API Group technology
Introduction of GORA API Group technology
Rakuten Group, Inc.
 
100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情
Rakuten Group, Inc.
 
社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー
Rakuten Group, Inc.
 

More from Rakuten Group, Inc. (20)

コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
 
楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり
 
What Makes Software Green?
What Makes Software Green?What Makes Software Green?
What Makes Software Green?
 
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
 
DataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組みDataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組み
 
大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開
 
楽天における大規模データベースの運用
楽天における大規模データベースの運用楽天における大規模データベースの運用
楽天における大規模データベースの運用
 
楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー
 
楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割
 
Rakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdfRakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdf
 
The Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdfThe Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdf
 
Supporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdfSupporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdf
 
Making Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdfMaking Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdf
 
How We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdfHow We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdf
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech info
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech info
 
OWASPTop10_Introduction
OWASPTop10_IntroductionOWASPTop10_Introduction
OWASPTop10_Introduction
 
Introduction of GORA API Group technology
Introduction of GORA API Group technologyIntroduction of GORA API Group technology
Introduction of GORA API Group technology
 
100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情
 
社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー
 

Recently uploaded

By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
Matthew Sinclair
 
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AIEnchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Vladimir Iglovikov, Ph.D.
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
Neo4j
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
Aftab Hussain
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
mikeeftimakis1
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
Kari Kakkonen
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
名前 です男
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
SOFTTECHHUB
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
Quotidiano Piemontese
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Safe Software
 
Generative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to ProductionGenerative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to Production
Aggregage
 

Recently uploaded (20)

By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
 
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AIEnchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
 
Generative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to ProductionGenerative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to Production
 

Why is my machine learning model not being used ?

  • 1. Oct 27, 2018 Akanksha Tiwari Rakuten Institute of Technology Singapore
  • 2. 2 I have built a model to predict which customer will cancel their subscription ..why is marketing not using it? 1. Marketing team will not use the model if they don’t know what action to take on the predictions and why 2. Data Scientists can use model interpretation to help marketing team take action
  • 3. Video streaming platform that streams Asian content.
  • 4. 4 Customers pay monthly subscription fee to watch content Customers cancel subscription and leave + $ - $ CHURN
  • 5. 5 … Yes, sure. That sounds exciting Management Why don't we start using AI to identify which customers will churn next month ? Marketing
  • 6. 6 … Yes, sure. That sounds exciting Management Why don't we start using AI to identify which customers will churn next month ? Marketing Can you help identify customers who will churn next month? Data Scientist
  • 7. 7 … Sure. I can use past data to build a model to predict who will churn in the next month. Data Scientist
  • 8. 8 … FEATURES Video Viewing Behavior Click Stream Behavior Subscription Behavior Train the model on past subscribers Predict the probability to churn in the next month Model Outperforms vendor’s model
  • 10. 10 … If client is unable to action on predictions then the model will not be used How should the output of the model be used ? Given the high risk churners what should I do and why? Marketing
  • 11. 11 Customer Probability to churn X 0.27 Y 0.86 Z 0.82 CHURN MODEL PREDICTIONS
  • 12. 12 Customer Probability to churn Reason for prediction X 0.27 Used service for more than year, Actively watching content Y 0.86 New User, Cancelled in the past Z 0.82 Used service for more than year, Lost Interest CHURN MODEL PREDICTIONS EXPLANATION
  • 13. 13 MODEL INTERPRETATION Model Interpretation of a machine learning model is how humans can understand the choices made by the model in the decision making process MODEL PREDICTIONS EXPLANATION
  • 14. 14
  • 15. 15 *(see the SHAP NIPS paper for details). SHAP*: • Latest work on model interpretation • Explains the output of any machine learning model. • Connects game theory with model explanations • Unifies several previous methods (such as LIME, DeepLift)
  • 16. 16 Member A What is an individual’s contribution in the team? Team makes $400 profits Member B Member C
  • 17. 17 Mapping teams to model prediction (Example) Team Members  Features used for a prediction Team sales  Prediction Score Member A Member A Member A $400 0.78 Days since subscription Minutes Viewed Number of past subscriptions
  • 18. 18 1: Calculate Normalizing Weights for all sub-sizes of teams Team Size Normalizing Weight* Team Permutations 1 2 3 33% 16% 33% *Normalizing Weight = m! x (n-m-1)! / n! n = size of original team m = size of team player get’s added to
  • 19. 19 2: Contribution when each member is working alone $200 $100 $0 Member A Member B Member C
  • 20. 20 3: Contribution of players as part of teams B’s contribution (in a team with A) = 400 - 200 = $200 A’s contribution (in a team with B) = 400 - 100 = $300 + = $400 Member A Member B
  • 21. 21 4: Final contributions Final SHAP AttributionsNormalizing Weights Team of 1 $200 $100 $0 33% 16% 33% $200 + $300 = $500 =$300 $0 $300 $200 $0 Team of 2 Team of 3 33% x $200 + 16% x $500 + 33% x $300 = $250 = $0 = $150 Member A Member B Member C
  • 22. 22 No. of past cancellations = 5 Prediction with a high churn score
  • 23. 23 Explanation of the prediction of the high churn score days since subscription = 25 Minutes viewed last quarter (of subscription) = 0 No. of past cancellations = 5
  • 24. 24 Days since subscription = 311 Minutes viewed last quarter (of subscription) = 3751 Days since last watched video = 0 Sample explanation of a low churn score
  • 25. 25 Flip the horizontal predictions vertically
  • 26. 26 Group all predictions by their SHAP values
  • 27. 27 Days since subscription = 31 days Minutes viewed last quarter = 0 New users, not watching content Higher lower S H A P V A L U E S USERS Helps marketing understand the decisions of the model
  • 28. 28 Disengaged users Higher lower Days since subscription = 301 Drop in minutes watched > 50% Minutes viewed last quarter = 0 USERS S H A P V A L U E S Helps marketing understand the decisions of the model and take action
  • 29. 29 Marketing Planning a campaign for disengaged users using content recommendation Acquisition Date: 24th Sep 2018
  • 30. 30 Revisit model / data Higher lower Minutes viewed in 2nd quarter of subscription = 1000 Minutes viewed drop > 50 % Minutes viewed in last quarter = 0 S H A P V A L U E S Helps in in Qualitative Model Evaluation
  • 31. 31 • Churn prediction is just one component of churn management • Marketing will not use the model if they don’t know what action to take on the predictions and why • Use model interpretation to help marketing take action