SlideShare uma empresa Scribd logo
1 de 30
“From zero to
hero”
in early life customer
segmentation
1. What is Super in Superbet?
2. Why would a segmentation topic be interesting?
3. What are the steps to take?
4. How to put first model out?
5. Can it be any better?
Agenda
What is Super in
Superbet?
Superbet? Betting/Gaming company, here on Codiax?
• 150+ people in Tech development
• Product oriented company
• 4.7 bil euro turnover in 2020
• 250% growth YoY
• 300+k active Online users
• Offices in 6 locations across Europe
(Poland, Romania, Croatia,
London/Leeds, Slovakia)
... rapid growth is yet to start!
(C)SUPERBET 2021 4
Superbet is on a mission to excite the world
Why would a
segmentation topic
be interesting?
Who are we actually up against?
Best customers
• Small in number
• Have preference for better product,
which we are trying to build
• Having the best ARPU
Worst customers
• Can do a lot of damage to the
business
• Trying to exploit holes in our
proposition
(C)SUPERBET 2021 6
2
3
Who are we actually up against?
One VIP customer brings a lot of
value to the company!
(C)SUPERBET 2021 7
A lot of customers are posing risk
to our business without brining
value in!
We want to focus on extremes!
2
3
What is the proces we are trying to improve?
Arbers and bonus abusers
• Manual segmentation from trading
team
• Depending on betting behaviour,
they are segmented within first
couple of days of activity
• Betting on low profile matches
• Trying to „bet against“ Superbet
Most valuable players – VIP
• CRM segmentation based on value
done once a month (cca 30 days to
segmentation of VIP, possibly more)
• VIP player gets private account
manager so we cannot segment
everyone
• High bets, similar to arbers (most
often, different events)
(C)SUPERBET 2021 8
What are the steps
to take?
• Analyse data and see if we can find patterns in it
• Create and test hypothesis based on patterns
• Create a predictive model that solves the problem
• Optimise and tune the model
• Push it to production
So, what do we need to do?
(C)SUPERBET 2021 10
What did we forget?
• Collect data you think you will need
• Store data on daily basis, or in real time
• Clean the data and prepare it for analysis
• Analyse data and see if we can find patterns in it
• Create and test hypothesis based on patterns
• Create a predictive model that solves the problem
• Optimise and tune the model
• Push it to production
• Serve recommendations to business units
(C)SUPERBET 2021 11
How to put first
model out?
1. Collect and store data
2. Clean the data and organize it
3. Get more data in
4. Create the first model
5. Push model to production
Agenda
Glossary
• (AWS) – Amazon Web Services ☺
• (AWS) EC2 – basically a virtual machine in the cloud
• (AWS) ECS – in essence, computing capacity “on-demand”
• (AWS) S3 – Object storage service
• (AWS) Lambda – event-driven, serverless computing platform
• (AWS) Glue – “ETL” tool within AWS stack
• (AWS) Sagemaker – jupyter notebook equivalent on AWS
• (Other) Vertica – analytical database that offers high performance
• (Other) Airflow – scheduling engine built with Python that can be enhanced
• (Other) Github - ?
• (Other) Kafka - ??
• (Other) Python - ???
(C)SUPERBET 2021 14
Collect and store data
(C)SUPERBET 2021 15
Collect and store data
(C)SUPERBET 2021 16
1 Python app = 1 Kafka topic
Vertica DB = 1 table per topic
S3 buckets = 1 bucket for full
history of data
50mil records per day – only
last message is relevant
= Data is ready to be used and
analysed!
Clean the data and organize it
(C)SUPERBET 2021 17
• ETL tool? ELT tool? We
need T tool, can we do
that? - enter Airflow
framework with Github
• Apache Airflow is used
for orchestration Full
historization of
transformation queries
on Github
= Vertica gets specific data
marts with star schema
instead of 100 messages for 1
ticket
Analysing data... Please hold!
(C)SUPERBET 2021 18
Hey, in first couple of days all customers
look similar with a bunch of anomalies...
Can we have a different perspective on the
customer?
(C)SUPERBET 2021 19
Get more data in
(C)SUPERBET 2021 20
• “Real behaviour data in
online is very hard to have!”
– unless you can use
Firebase/Google analytics
• Not all Supercompanies run
Kafka, some are still working
with “normal” databases –
that is fine!
= More behavioural data can
help segment the customers
better and give a bunch of
new insights
Now this makes much more sense!
(C)SUPERBET 2021 21
Create the first model
(C)SUPERBET 2021 22
• Use your laptop, don’t
overcomplicate
• When things get tough,
give it more power – enter
EC2 (or ECS*)
• For obfuscators – there is
also AWS Sagemaker,
Disneyland for people who
love coding and
infrastructure
Push model to production
(C)SUPERBET 2021 23
• Create a docker image
that can run your model
• Use existing environments
to execute workload
• Use existing scheduler to
optimize process
• Integrate findings within
Tableau or push directly
into platform (you are
guessing – Python
application!)
Spotting suspicious customers with 90%+
accuracy* after first bet placed, and
potential VIP players with 75% accuracy*
after 2 weeks of activity!
(C)SUPERBET 2021 24
Can it be any
better?
What do we need to improve
From batch to real
time –
orchestration!
(C)SUPERBET 2021 26
Add more data
analysis in, enrich
knowledge about
customers! Scalability to cover
business growth
How to do this in real time?
(C)SUPERBET 2021 27
Something else to add?
• Think all of this is stupid? Reach out, would like to hear your thoughts!
• Think all of this is brilliant? Reach out, glad to explain more where
needed!
(C)SUPERBET 2021 28
Want to excite the world? Reach out and join us! Plenty of open
possitions are waiting!
Something else to add?
• Think all of this is stupid? Reach out, would like to hear your thoughts!
• Think all of this is brilliant? Reach out, glad to explain more where
needed!
• Looking for analytical database? Vertica is awesome, but also look for
Snowflake
• Kafka Connect exists – you dont need to code all those consumer apps
• Airflow alternative? Prefect!
• Dont have data in Kafka topics? Google: „How to push CDC logs into Kafka“
• Want to avoid Glue? Be careful with Bigquery ☺
(C)SUPERBET 2021 29
Want to excite the world? Reach out and join us! Plenty of open
possitions are waiting!
Thank you!

Mais conteúdo relacionado

Semelhante a Luka Postružin (Superbet) – ‘From zero to hero’ in early life customer segmentation

Making operations visible - devopsdays tokyo 2013
Making operations visible  - devopsdays tokyo 2013Making operations visible  - devopsdays tokyo 2013
Making operations visible - devopsdays tokyo 2013
Nick Galbreath
 
Making operations visible - Nick Gallbreath
Making operations visible - Nick GallbreathMaking operations visible - Nick Gallbreath
Making operations visible - Nick Gallbreath
Devopsdays
 

Semelhante a Luka Postružin (Superbet) – ‘From zero to hero’ in early life customer segmentation (20)

Digital Success Stack for DCBKK 2018
Digital Success Stack for DCBKK 2018Digital Success Stack for DCBKK 2018
Digital Success Stack for DCBKK 2018
 
Minimum viable product to delivery business value
Minimum viable product to delivery business valueMinimum viable product to delivery business value
Minimum viable product to delivery business value
 
Playing to Win: Turbocharged Tableau with a GPU Database
Playing to Win: Turbocharged Tableau with a GPU DatabasePlaying to Win: Turbocharged Tableau with a GPU Database
Playing to Win: Turbocharged Tableau with a GPU Database
 
The Future of ETL Isn't What It Used to Be
The Future of ETL Isn't What It Used to BeThe Future of ETL Isn't What It Used to Be
The Future of ETL Isn't What It Used to Be
 
From 6 hours to 1 minute... in 2 days! How we managed to stream our (long) Ha...
From 6 hours to 1 minute... in 2 days! How we managed to stream our (long) Ha...From 6 hours to 1 minute... in 2 days! How we managed to stream our (long) Ha...
From 6 hours to 1 minute... in 2 days! How we managed to stream our (long) Ha...
 
Big Data Berlin - Criteo
Big Data Berlin - CriteoBig Data Berlin - Criteo
Big Data Berlin - Criteo
 
Alternative microservices - one size doesn't fit all
Alternative microservices - one size doesn't fit allAlternative microservices - one size doesn't fit all
Alternative microservices - one size doesn't fit all
 
Making operations visible - devopsdays tokyo 2013
Making operations visible  - devopsdays tokyo 2013Making operations visible  - devopsdays tokyo 2013
Making operations visible - devopsdays tokyo 2013
 
Making operations visible - Nick Gallbreath
Making operations visible - Nick GallbreathMaking operations visible - Nick Gallbreath
Making operations visible - Nick Gallbreath
 
TIBCO Advanced Analytics Meetup (TAAM) - June 2015
TIBCO Advanced Analytics Meetup (TAAM) - June 2015TIBCO Advanced Analytics Meetup (TAAM) - June 2015
TIBCO Advanced Analytics Meetup (TAAM) - June 2015
 
Games Industry Analytics Forum 2 - Plumbee
Games Industry Analytics Forum 2 - PlumbeeGames Industry Analytics Forum 2 - Plumbee
Games Industry Analytics Forum 2 - Plumbee
 
Simplifying Use of Hive with the Hive Query Tool
Simplifying Use of Hive with the Hive Query ToolSimplifying Use of Hive with the Hive Query Tool
Simplifying Use of Hive with the Hive Query Tool
 
Pragmatic Machine Learning @ ML Spain
Pragmatic Machine Learning @ ML SpainPragmatic Machine Learning @ ML Spain
Pragmatic Machine Learning @ ML Spain
 
Data Science and Enterprise Engineering with Michael Finger and Chris Robison
Data Science and Enterprise Engineering with Michael Finger and Chris RobisonData Science and Enterprise Engineering with Michael Finger and Chris Robison
Data Science and Enterprise Engineering with Michael Finger and Chris Robison
 
Integrating IBM Cognos 10 into Microsoft Office
Integrating IBM Cognos 10 into Microsoft OfficeIntegrating IBM Cognos 10 into Microsoft Office
Integrating IBM Cognos 10 into Microsoft Office
 
Maintainable Machine Learning Products
Maintainable Machine Learning ProductsMaintainable Machine Learning Products
Maintainable Machine Learning Products
 
DOES16 London - Jonathan Fletcher - Re-imagining Hiscox IT: A DevOps Story
DOES16 London - Jonathan Fletcher - Re-imagining Hiscox IT: A DevOps StoryDOES16 London - Jonathan Fletcher - Re-imagining Hiscox IT: A DevOps Story
DOES16 London - Jonathan Fletcher - Re-imagining Hiscox IT: A DevOps Story
 
Creating a Culture of Data @ Facebook - TCCEU13
Creating a Culture of Data @ Facebook - TCCEU13Creating a Culture of Data @ Facebook - TCCEU13
Creating a Culture of Data @ Facebook - TCCEU13
 
Data modeling trends for Analytics
Data modeling trends for AnalyticsData modeling trends for Analytics
Data modeling trends for Analytics
 
How we integrate Machine Learning Algorithms into our IT Platform at Outfittery
How we integrate Machine Learning Algorithms into our IT Platform at OutfitteryHow we integrate Machine Learning Algorithms into our IT Platform at Outfittery
How we integrate Machine Learning Algorithms into our IT Platform at Outfittery
 

Mais de Codiax

Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...
Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...
Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...
Codiax
 
Costas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluation
Costas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluationCostas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluation
Costas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluation
Codiax
 
Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...
Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...
Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...
Codiax
 
Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...
Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...
Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...
Codiax
 
Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...
Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...
Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...
Codiax
 
Adria Recasens, DeepMind – Multi-modal self-supervised learning from videos
Adria Recasens, DeepMind – Multi-modal self-supervised learning from videosAdria Recasens, DeepMind – Multi-modal self-supervised learning from videos
Adria Recasens, DeepMind – Multi-modal self-supervised learning from videos
Codiax
 
Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...
Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...
Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...
Codiax
 
Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...
Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...
Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...
Codiax
 
Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...
Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...
Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...
Codiax
 
Matthias Feys (ML6) – Bias in ML: A Technical Intro
Matthias Feys (ML6) – Bias in ML: A Technical IntroMatthias Feys (ML6) – Bias in ML: A Technical Intro
Matthias Feys (ML6) – Bias in ML: A Technical Intro
Codiax
 
Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...
Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...
Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...
Codiax
 
Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...
Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...
Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...
Codiax
 
Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...
Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...
Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...
Codiax
 
Maciej Marek (Philip Morris International) - The Tools of The Trade
Maciej Marek (Philip Morris International) - The Tools of The TradeMaciej Marek (Philip Morris International) - The Tools of The Trade
Maciej Marek (Philip Morris International) - The Tools of The Trade
Codiax
 
Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...
Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...
Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...
Codiax
 
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Codiax
 
Jakub Bartoszek (Samsung Electronics) - Hardware Security in Connected World
Jakub Bartoszek (Samsung Electronics) - Hardware Security in Connected WorldJakub Bartoszek (Samsung Electronics) - Hardware Security in Connected World
Jakub Bartoszek (Samsung Electronics) - Hardware Security in Connected World
Codiax
 
Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...
Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...
Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...
Codiax
 
Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?
Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?
Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?
Codiax
 
Alexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network Server
Alexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network ServerAlexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network Server
Alexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network Server
Codiax
 

Mais de Codiax (20)

Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...
Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...
Dr. Laura Kerber (NASA’s Jet Propulsion Laboratory) – Exploring Caves on the ...
 
Costas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluation
Costas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluationCostas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluation
Costas Voliotis (CodeWeTrust) – An AI-driven approach to source code evaluation
 
Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...
Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...
Dr. Lobna Karoui (Fortune 500) – Disruption, empathy & Trust for sustainable ...
 
Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...
Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...
Gema Parreno Piqueras (Apium Hub) – Videogames and Interactive Narrative Cont...
 
Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...
Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...
Janos Puskas (Accenture) – Azure IoT Reference Architecture for enterprise Io...
 
Adria Recasens, DeepMind – Multi-modal self-supervised learning from videos
Adria Recasens, DeepMind – Multi-modal self-supervised learning from videosAdria Recasens, DeepMind – Multi-modal self-supervised learning from videos
Adria Recasens, DeepMind – Multi-modal self-supervised learning from videos
 
Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...
Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...
Roelof Pieters (Overstory) – Tackling Forest Fires and Deforestation with Sat...
 
Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...
Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...
Javier Fuentes Alonso (Uizard) – Using machine learning to turn you into a de...
 
Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...
Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...
Emeli Dral (Evidently AI) – Analyze it: production monitoring for machine lea...
 
Matthias Feys (ML6) – Bias in ML: A Technical Intro
Matthias Feys (ML6) – Bias in ML: A Technical IntroMatthias Feys (ML6) – Bias in ML: A Technical Intro
Matthias Feys (ML6) – Bias in ML: A Technical Intro
 
Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...
Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...
Christophe Tallec, Hello Tomorrow – Solving our next decade challenges throug...
 
Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...
Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...
Sean Holden (University of Cambridge) - Proving Theorems_ Still A Major Test ...
 
Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...
Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...
Olga Afanasjeva (GoodAI) - Towards general artificial intelligence for common...
 
Maciej Marek (Philip Morris International) - The Tools of The Trade
Maciej Marek (Philip Morris International) - The Tools of The TradeMaciej Marek (Philip Morris International) - The Tools of The Trade
Maciej Marek (Philip Morris International) - The Tools of The Trade
 
Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...
Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...
Joanna Bryson (University of Bath) - Intelligence by Design_ Systems engineer...
 
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
 
Jakub Bartoszek (Samsung Electronics) - Hardware Security in Connected World
Jakub Bartoszek (Samsung Electronics) - Hardware Security in Connected WorldJakub Bartoszek (Samsung Electronics) - Hardware Security in Connected World
Jakub Bartoszek (Samsung Electronics) - Hardware Security in Connected World
 
Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...
Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...
Jair Ribeiro - Defining a Successful Artificial Intelligence Strategy for you...
 
Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?
Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?
Cindy Spelt (Zoom In Zoom Out) - How to beat the face recognition challenges?
 
Alexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network Server
Alexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network ServerAlexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network Server
Alexey Borisenko (Cisco) - Creating IoT solution using LoRaWAN Network Server
 

Último

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Último (20)

Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot ModelNavi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 

Luka Postružin (Superbet) – ‘From zero to hero’ in early life customer segmentation

  • 1. “From zero to hero” in early life customer segmentation
  • 2. 1. What is Super in Superbet? 2. Why would a segmentation topic be interesting? 3. What are the steps to take? 4. How to put first model out? 5. Can it be any better? Agenda
  • 3. What is Super in Superbet?
  • 4. Superbet? Betting/Gaming company, here on Codiax? • 150+ people in Tech development • Product oriented company • 4.7 bil euro turnover in 2020 • 250% growth YoY • 300+k active Online users • Offices in 6 locations across Europe (Poland, Romania, Croatia, London/Leeds, Slovakia) ... rapid growth is yet to start! (C)SUPERBET 2021 4 Superbet is on a mission to excite the world
  • 5. Why would a segmentation topic be interesting?
  • 6. Who are we actually up against? Best customers • Small in number • Have preference for better product, which we are trying to build • Having the best ARPU Worst customers • Can do a lot of damage to the business • Trying to exploit holes in our proposition (C)SUPERBET 2021 6 2 3
  • 7. Who are we actually up against? One VIP customer brings a lot of value to the company! (C)SUPERBET 2021 7 A lot of customers are posing risk to our business without brining value in! We want to focus on extremes! 2 3
  • 8. What is the proces we are trying to improve? Arbers and bonus abusers • Manual segmentation from trading team • Depending on betting behaviour, they are segmented within first couple of days of activity • Betting on low profile matches • Trying to „bet against“ Superbet Most valuable players – VIP • CRM segmentation based on value done once a month (cca 30 days to segmentation of VIP, possibly more) • VIP player gets private account manager so we cannot segment everyone • High bets, similar to arbers (most often, different events) (C)SUPERBET 2021 8
  • 9. What are the steps to take?
  • 10. • Analyse data and see if we can find patterns in it • Create and test hypothesis based on patterns • Create a predictive model that solves the problem • Optimise and tune the model • Push it to production So, what do we need to do? (C)SUPERBET 2021 10
  • 11. What did we forget? • Collect data you think you will need • Store data on daily basis, or in real time • Clean the data and prepare it for analysis • Analyse data and see if we can find patterns in it • Create and test hypothesis based on patterns • Create a predictive model that solves the problem • Optimise and tune the model • Push it to production • Serve recommendations to business units (C)SUPERBET 2021 11
  • 12. How to put first model out?
  • 13. 1. Collect and store data 2. Clean the data and organize it 3. Get more data in 4. Create the first model 5. Push model to production Agenda
  • 14. Glossary • (AWS) – Amazon Web Services ☺ • (AWS) EC2 – basically a virtual machine in the cloud • (AWS) ECS – in essence, computing capacity “on-demand” • (AWS) S3 – Object storage service • (AWS) Lambda – event-driven, serverless computing platform • (AWS) Glue – “ETL” tool within AWS stack • (AWS) Sagemaker – jupyter notebook equivalent on AWS • (Other) Vertica – analytical database that offers high performance • (Other) Airflow – scheduling engine built with Python that can be enhanced • (Other) Github - ? • (Other) Kafka - ?? • (Other) Python - ??? (C)SUPERBET 2021 14
  • 15. Collect and store data (C)SUPERBET 2021 15
  • 16. Collect and store data (C)SUPERBET 2021 16 1 Python app = 1 Kafka topic Vertica DB = 1 table per topic S3 buckets = 1 bucket for full history of data 50mil records per day – only last message is relevant = Data is ready to be used and analysed!
  • 17. Clean the data and organize it (C)SUPERBET 2021 17 • ETL tool? ELT tool? We need T tool, can we do that? - enter Airflow framework with Github • Apache Airflow is used for orchestration Full historization of transformation queries on Github = Vertica gets specific data marts with star schema instead of 100 messages for 1 ticket
  • 18. Analysing data... Please hold! (C)SUPERBET 2021 18
  • 19. Hey, in first couple of days all customers look similar with a bunch of anomalies... Can we have a different perspective on the customer? (C)SUPERBET 2021 19
  • 20. Get more data in (C)SUPERBET 2021 20 • “Real behaviour data in online is very hard to have!” – unless you can use Firebase/Google analytics • Not all Supercompanies run Kafka, some are still working with “normal” databases – that is fine! = More behavioural data can help segment the customers better and give a bunch of new insights
  • 21. Now this makes much more sense! (C)SUPERBET 2021 21
  • 22. Create the first model (C)SUPERBET 2021 22 • Use your laptop, don’t overcomplicate • When things get tough, give it more power – enter EC2 (or ECS*) • For obfuscators – there is also AWS Sagemaker, Disneyland for people who love coding and infrastructure
  • 23. Push model to production (C)SUPERBET 2021 23 • Create a docker image that can run your model • Use existing environments to execute workload • Use existing scheduler to optimize process • Integrate findings within Tableau or push directly into platform (you are guessing – Python application!)
  • 24. Spotting suspicious customers with 90%+ accuracy* after first bet placed, and potential VIP players with 75% accuracy* after 2 weeks of activity! (C)SUPERBET 2021 24
  • 25. Can it be any better?
  • 26. What do we need to improve From batch to real time – orchestration! (C)SUPERBET 2021 26 Add more data analysis in, enrich knowledge about customers! Scalability to cover business growth
  • 27. How to do this in real time? (C)SUPERBET 2021 27
  • 28. Something else to add? • Think all of this is stupid? Reach out, would like to hear your thoughts! • Think all of this is brilliant? Reach out, glad to explain more where needed! (C)SUPERBET 2021 28 Want to excite the world? Reach out and join us! Plenty of open possitions are waiting!
  • 29. Something else to add? • Think all of this is stupid? Reach out, would like to hear your thoughts! • Think all of this is brilliant? Reach out, glad to explain more where needed! • Looking for analytical database? Vertica is awesome, but also look for Snowflake • Kafka Connect exists – you dont need to code all those consumer apps • Airflow alternative? Prefect! • Dont have data in Kafka topics? Google: „How to push CDC logs into Kafka“ • Want to avoid Glue? Be careful with Bigquery ☺ (C)SUPERBET 2021 29 Want to excite the world? Reach out and join us! Plenty of open possitions are waiting!