SlideShare une entreprise Scribd logo
1  sur  19
Télécharger pour lire hors ligne
AI-driven personalised email marketing
2
AI-driven Personalised Marketing
Who is Endeavour Group Limited?
Endeavour Groups Limited, is Australia’s largest drinks retailer with over 2000 venues across a wide range of brands.
The EGL team has built a personalisation marketing engine using Databricks that performs segmentation of EGLs 4.5
million loyalty members. Personalisation is one of most important strategic investments in EGL and is expected to
significantly increase revenue and improve customer experience.
This session will dive into how EGL has been able to develop effective brand campaigns that target the right people,
at the right time with the right messages to millions of their loyalty members. EGL utilizes cutting edge reinforcement
learning as a paradigm for Personalization Engine based on data. The Engine elegantly links marketing logics, AI and
business processes together, and strives to intelligently determine the balance between the discovery and relevancy
of email campaigns.
3
AI-driven Personalised Marketing
Topics
What problems are we solving?
How to use AI to drive personalised marketing?
What does our AI solution look like?
What are the challenges and how we solved them?
Personalised marketing: Who, What When. When to send, what email to use and with what
products?
We use AI to determine which is the best email template to send a customer
Huge data volumes for the model to learn and make predictions
We combine reinforcement learning, a recommendation engine and business logic to solve the challenging problem.
4
What problem are we solving
Personalised email marketing
● What is the theme of the email?
● What products should be in the email?
● Whom to send the email?
● When to send the email?
What are the problems we are
solving?
Place your image on top of grey square.
OR use Layout: 1 Col/Right Image with Image Layout.
5
What problem are we solving
… products that the customers are likely to
buy, which they have purchased before.
What products should we
show to who?
Past purchase history Demographics
XGBoost model
Ranks of the likelihood of purchase
Buy it again and save!!!
Easy!
Place your image on top of grey square.
OR use Layout: 1 Col/Right Image with Image Layout.
6
What problem are we solving
You have bought this ...
Why not try this … ?
… products that the customers are likely to
buy, which they have NOT purchased
before.
What products should we
show to who?
Past
purchases
Products
attributes
XGBoost
Ranks of the likelihood of purchase
Marketing
response Seasonality
Harder!
Place your image on top of grey square.
OR use Layout: 1 Col/Right Image with Image Layout.
7
What problem are we solving
… 3 out of 2000 emails that you are more
likely to click and then buy
What is the theme of the
email?
Past
purchases
Products
attributes
Multi-armed bandit
Likelihood of click + buy the product in the
email
Marketing
response
Email
attributes
Hardest!
Place your image on top of grey square.
OR use Layout: 1 Col/Right Image with Image Layout.
8
What problem are we solving
What time should we send the
email Easy!
No AI yet..
… just pick 35 random time slots in a week!
The next step is to use AI to identify the time
slots and frequency that customers will click
and buy the product …
… and will not lead to unsubscribe!
9
There are three key components in our Personalisation
Email Examples - Mega-Intro + Christmas Content
relevance
->
previously
purchased
generic
discovery_seg
->
recommended—single
category
discovery
->
recommended—cross
category
11
12
Let’s get into the
nitty-gritty
technical details!
13
How does our AI solution look like?
Thompson algorithm
We structure the email selection as an multi-armed bandit
problem and use Thompson algorithm as the solution.
We model it as a Multi-Armed
Bandit (MAB problem
Bandit
70%
Current
success
rate
Bandit
30%
Current
success
rate
Bandit
50%
Current
success
rate
Next choice?
Decision
making MAB
Optimisation
Choose the best product
By finding the best emails
Minimise the total regrets
By avoiding sending bad emails
as much as possible
14
What are the challenges and how to solve them
It was a tough decision between cold start v.s. warm start
15
Exploration v.s. experimentation
16
How does our AI solution look like?
… we have to wait and see
It was not easy to balance between exploration and exploitation
for a multi-armed bandit problem...
17
What are the challenges and how to solve them
Algorithms and technologies are just parts of the puzzle, there are
many business processes need to be considered or adjusted.
● There are some time sensitive emails which we want to send more of it in a short amount of
time, e.g. Easter. We upweight those actions so they get higher rankings. The upweight is
chosen in a way to minimize the clicks lost whilst getting our desired amount of sends.
Additional
email
sent
Upweight level
18
What are the challenges and how to solve them
Algorithms and technologies are just parts of the puzzle, there are
many business processes need to be considered or adjusted.
Are we sending too many emails that
cause unsubscription?
Do we send the same emails over and
over again?
How do we bring customers to a
pleasant journey, e.g. onboarding
How can we treat a cohort differently if the
incremental sales are not the focus, e.g. retention
How can we deliver consistent messages across all
channels?
How do we choose emails that a model has never
seen before?
AI-driven Personalised Marketing
What’s next in the EGL personalisation Journey
Personalised landing page
Personalised searching results
Personalised customer review
Personalised basket building
Personalised customer retention
Personalised journey
Personalised App push notifications
Personalised offer
19

Contenu connexe

Tendances

ODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptx
ODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptxODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptx
ODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptxKuldeep Jiwani
 
Causal Inference : Primer (2019-06-01 잔디콘)
Causal Inference : Primer (2019-06-01 잔디콘)Causal Inference : Primer (2019-06-01 잔디콘)
Causal Inference : Primer (2019-06-01 잔디콘)Minho Lee
 
Recommendation Modeling with Impression Data at Netflix
Recommendation Modeling with Impression Data at NetflixRecommendation Modeling with Impression Data at Netflix
Recommendation Modeling with Impression Data at NetflixJiangwei Pan
 
[PAP] 실무자를 위한 인과추론 활용 : Best Practices
[PAP] 실무자를 위한 인과추론 활용 : Best Practices[PAP] 실무자를 위한 인과추론 활용 : Best Practices
[PAP] 실무자를 위한 인과추론 활용 : Best PracticesBokyung Choi
 
하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018
하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018
하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018승호 박
 
딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)
딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)
딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)WON JOON YOO
 
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.Yongho Ha
 
Prompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowaniaPrompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowaniaMichal Jaskolski
 
Natural language processing and transformer models
Natural language processing and transformer modelsNatural language processing and transformer models
Natural language processing and transformer modelsDing Li
 
PPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebe
PPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebePPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebe
PPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebeTaste
 
SmartNews TechNight vol5 SmartNews Ads大図解
SmartNews TechNight vol5 SmartNews Ads大図解SmartNews TechNight vol5 SmartNews Ads大図解
SmartNews TechNight vol5 SmartNews Ads大図解SmartNews, Inc.
 
Real-world Reinforcement Learning
Real-world Reinforcement LearningReal-world Reinforcement Learning
Real-world Reinforcement LearningMax Pagels
 
Topic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic ModelsTopic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic ModelsClaudia Wagner
 
Learning to Rank - From pairwise approach to listwise
Learning to Rank - From pairwise approach to listwiseLearning to Rank - From pairwise approach to listwise
Learning to Rank - From pairwise approach to listwiseHasan H Topcu
 
Episode 2: The LLM / GPT / AI Prompt / Data Engineer Roadmap
Episode 2: The LLM / GPT / AI Prompt / Data Engineer RoadmapEpisode 2: The LLM / GPT / AI Prompt / Data Engineer Roadmap
Episode 2: The LLM / GPT / AI Prompt / Data Engineer RoadmapAnant Corporation
 
Tutorial on Question Answering Systems
Tutorial on Question Answering Systems Tutorial on Question Answering Systems
Tutorial on Question Answering Systems Saeedeh Shekarpour
 
LinkedIn talk at Netflix ML Platform meetup Sep 2019
LinkedIn talk at Netflix ML Platform meetup Sep 2019LinkedIn talk at Netflix ML Platform meetup Sep 2019
LinkedIn talk at Netflix ML Platform meetup Sep 2019Faisal Siddiqi
 
[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP
[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP
[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLPJoeun Park
 
Beyond Churn Prediction : An Introduction to uplift modeling
Beyond Churn Prediction : An Introduction to uplift modelingBeyond Churn Prediction : An Introduction to uplift modeling
Beyond Churn Prediction : An Introduction to uplift modelingPierre Gutierrez
 
Marketplace in motion - AdKDD keynote - 2020
Marketplace in motion - AdKDD keynote - 2020 Marketplace in motion - AdKDD keynote - 2020
Marketplace in motion - AdKDD keynote - 2020 Roelof van Zwol
 

Tendances (20)

ODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptx
ODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptxODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptx
ODSC APAC 2023: LLMs & Ontologies for Precision NERC.pptx
 
Causal Inference : Primer (2019-06-01 잔디콘)
Causal Inference : Primer (2019-06-01 잔디콘)Causal Inference : Primer (2019-06-01 잔디콘)
Causal Inference : Primer (2019-06-01 잔디콘)
 
Recommendation Modeling with Impression Data at Netflix
Recommendation Modeling with Impression Data at NetflixRecommendation Modeling with Impression Data at Netflix
Recommendation Modeling with Impression Data at Netflix
 
[PAP] 실무자를 위한 인과추론 활용 : Best Practices
[PAP] 실무자를 위한 인과추론 활용 : Best Practices[PAP] 실무자를 위한 인과추론 활용 : Best Practices
[PAP] 실무자를 위한 인과추론 활용 : Best Practices
 
하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018
하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018
하이퍼커넥트에서 자동 광고 측정 서비스 구현하기 - PyCon Korea 2018
 
딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)
딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)
딥 러닝 자연어 처리를 학습을 위한 파워포인트. (Deep Learning for Natural Language Processing)
 
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
 
Prompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowaniaPrompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowania
 
Natural language processing and transformer models
Natural language processing and transformer modelsNatural language processing and transformer models
Natural language processing and transformer models
 
PPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebe
PPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebePPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebe
PPC Restart 2023: Libor Mattuš - Optimalizujte nejen kampaně, ale i sebe
 
SmartNews TechNight vol5 SmartNews Ads大図解
SmartNews TechNight vol5 SmartNews Ads大図解SmartNews TechNight vol5 SmartNews Ads大図解
SmartNews TechNight vol5 SmartNews Ads大図解
 
Real-world Reinforcement Learning
Real-world Reinforcement LearningReal-world Reinforcement Learning
Real-world Reinforcement Learning
 
Topic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic ModelsTopic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic Models
 
Learning to Rank - From pairwise approach to listwise
Learning to Rank - From pairwise approach to listwiseLearning to Rank - From pairwise approach to listwise
Learning to Rank - From pairwise approach to listwise
 
Episode 2: The LLM / GPT / AI Prompt / Data Engineer Roadmap
Episode 2: The LLM / GPT / AI Prompt / Data Engineer RoadmapEpisode 2: The LLM / GPT / AI Prompt / Data Engineer Roadmap
Episode 2: The LLM / GPT / AI Prompt / Data Engineer Roadmap
 
Tutorial on Question Answering Systems
Tutorial on Question Answering Systems Tutorial on Question Answering Systems
Tutorial on Question Answering Systems
 
LinkedIn talk at Netflix ML Platform meetup Sep 2019
LinkedIn talk at Netflix ML Platform meetup Sep 2019LinkedIn talk at Netflix ML Platform meetup Sep 2019
LinkedIn talk at Netflix ML Platform meetup Sep 2019
 
[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP
[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP
[싸이그램즈 2018] 텍스트 데이터 전처리로 시작하는 NLP
 
Beyond Churn Prediction : An Introduction to uplift modeling
Beyond Churn Prediction : An Introduction to uplift modelingBeyond Churn Prediction : An Introduction to uplift modeling
Beyond Churn Prediction : An Introduction to uplift modeling
 
Marketplace in motion - AdKDD keynote - 2020
Marketplace in motion - AdKDD keynote - 2020 Marketplace in motion - AdKDD keynote - 2020
Marketplace in motion - AdKDD keynote - 2020
 

Similaire à AI-Driven Personalized Email Marketing

SmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum Marketing
SmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum MarketingSmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum Marketing
SmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum MarketingMarketing Network marcus evans
 
How To Sell To Businesses - Sales Advice for Startups
How To Sell To Businesses - Sales Advice for StartupsHow To Sell To Businesses - Sales Advice for Startups
How To Sell To Businesses - Sales Advice for StartupsNicolas Deville
 
InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...
InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...
InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...Katie Martell
 
MarketingDataLake.pdf
MarketingDataLake.pdfMarketingDataLake.pdf
MarketingDataLake.pdfapurva joshi
 
Contact pigeon at Open Coffee Athens LXXIX
Contact pigeon at Open Coffee Athens LXXIXContact pigeon at Open Coffee Athens LXXIX
Contact pigeon at Open Coffee Athens LXXIXOpen Coffee Greece
 
[Webinar] Accelerating Customer Speed in Europe
[Webinar] Accelerating Customer Speed in Europe[Webinar] Accelerating Customer Speed in Europe
[Webinar] Accelerating Customer Speed in EuropeOptimizely
 
Building and scaling an acquisition marketing machine - seedcamp sept 2016
Building and scaling an acquisition marketing machine  -  seedcamp sept 2016Building and scaling an acquisition marketing machine  -  seedcamp sept 2016
Building and scaling an acquisition marketing machine - seedcamp sept 2016Depesh Mandalia
 
Marketing For microISVs
Marketing For microISVsMarketing For microISVs
Marketing For microISVsoryxdigital
 
The theory of marketing
The theory of marketingThe theory of marketing
The theory of marketingAli Syme
 
Growth marketing for corporates - Intro session - ING innovation leaders
Growth marketing for corporates - Intro session - ING innovation leadersGrowth marketing for corporates - Intro session - ING innovation leaders
Growth marketing for corporates - Intro session - ING innovation leadersGrowth Tribe
 
Why We Automate: Observations from billions of customer interactions
Why We Automate: Observations from billions of customer interactionsWhy We Automate: Observations from billions of customer interactions
Why We Automate: Observations from billions of customer interactionsMediaPost
 
Eis 2 fri_ vickyge
Eis 2 fri_ vickygeEis 2 fri_ vickyge
Eis 2 fri_ vickygeMediaPost
 
Using data analytics midlands think tank 2013
Using data analytics midlands think tank 2013Using data analytics midlands think tank 2013
Using data analytics midlands think tank 2013Paddy Moore
 
LTK - FC - Supply Chain - Startup Challenge v3.pdf
LTK - FC - Supply Chain - Startup Challenge v3.pdfLTK - FC - Supply Chain - Startup Challenge v3.pdf
LTK - FC - Supply Chain - Startup Challenge v3.pdfjeroen_tjepkema
 
Today and tomorrow in the world of email
Today and tomorrow in the world of emailToday and tomorrow in the world of email
Today and tomorrow in the world of emailPhillip Smith
 
Marketing Automation Summit 2015
Marketing Automation Summit 2015Marketing Automation Summit 2015
Marketing Automation Summit 2015Scopernia
 
The acquisition marketing puzzle most fail to complete - Turing Festival Augu...
The acquisition marketing puzzle most fail to complete - Turing Festival Augu...The acquisition marketing puzzle most fail to complete - Turing Festival Augu...
The acquisition marketing puzzle most fail to complete - Turing Festival Augu...Depesh Mandalia
 

Similaire à AI-Driven Personalized Email Marketing (20)

SmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum Marketing
SmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum MarketingSmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum Marketing
SmartBeemo: The World´s First Smart Posting Tool - David Uribe, Asylum Marketing
 
How To Sell To Businesses - Sales Advice for Startups
How To Sell To Businesses - Sales Advice for StartupsHow To Sell To Businesses - Sales Advice for Startups
How To Sell To Businesses - Sales Advice for Startups
 
InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...
InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...
InnovateEDU Bootcamp: 7 Questions Investors Will Ask About Your GoToMarket St...
 
MarketingDataLake.pdf
MarketingDataLake.pdfMarketingDataLake.pdf
MarketingDataLake.pdf
 
Contact pigeon at Open Coffee Athens LXXIX
Contact pigeon at Open Coffee Athens LXXIXContact pigeon at Open Coffee Athens LXXIX
Contact pigeon at Open Coffee Athens LXXIX
 
Confused @ oi15
Confused @ oi15Confused @ oi15
Confused @ oi15
 
How to Price what you Sell?
How to Price what you Sell?How to Price what you Sell?
How to Price what you Sell?
 
[Webinar] Accelerating Customer Speed in Europe
[Webinar] Accelerating Customer Speed in Europe[Webinar] Accelerating Customer Speed in Europe
[Webinar] Accelerating Customer Speed in Europe
 
Building and scaling an acquisition marketing machine - seedcamp sept 2016
Building and scaling an acquisition marketing machine  -  seedcamp sept 2016Building and scaling an acquisition marketing machine  -  seedcamp sept 2016
Building and scaling an acquisition marketing machine - seedcamp sept 2016
 
Marketing For microISVs
Marketing For microISVsMarketing For microISVs
Marketing For microISVs
 
The theory of marketing
The theory of marketingThe theory of marketing
The theory of marketing
 
Growth marketing for corporates - Intro session - ING innovation leaders
Growth marketing for corporates - Intro session - ING innovation leadersGrowth marketing for corporates - Intro session - ING innovation leaders
Growth marketing for corporates - Intro session - ING innovation leaders
 
Why We Automate: Observations from billions of customer interactions
Why We Automate: Observations from billions of customer interactionsWhy We Automate: Observations from billions of customer interactions
Why We Automate: Observations from billions of customer interactions
 
Eis 2 fri_ vickyge
Eis 2 fri_ vickygeEis 2 fri_ vickyge
Eis 2 fri_ vickyge
 
Using data analytics midlands think tank 2013
Using data analytics midlands think tank 2013Using data analytics midlands think tank 2013
Using data analytics midlands think tank 2013
 
LTK - FC - Supply Chain - Startup Challenge v3.pdf
LTK - FC - Supply Chain - Startup Challenge v3.pdfLTK - FC - Supply Chain - Startup Challenge v3.pdf
LTK - FC - Supply Chain - Startup Challenge v3.pdf
 
Today and tomorrow in the world of email
Today and tomorrow in the world of emailToday and tomorrow in the world of email
Today and tomorrow in the world of email
 
Marketing Automation Summit 2015
Marketing Automation Summit 2015Marketing Automation Summit 2015
Marketing Automation Summit 2015
 
Graphic Design
Graphic DesignGraphic Design
Graphic Design
 
The acquisition marketing puzzle most fail to complete - Turing Festival Augu...
The acquisition marketing puzzle most fail to complete - Turing Festival Augu...The acquisition marketing puzzle most fail to complete - Turing Festival Augu...
The acquisition marketing puzzle most fail to complete - Turing Festival Augu...
 

Plus de Databricks

DW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptxDW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptxDatabricks
 
Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1Databricks
 
Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Databricks
 
Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2Databricks
 
Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4Databricks
 
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of HadoopDatabricks
 
Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDatabricks
 
Learn to Use Databricks for Data Science
Learn to Use Databricks for Data ScienceLearn to Use Databricks for Data Science
Learn to Use Databricks for Data ScienceDatabricks
 
Why APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML MonitoringWhy APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML MonitoringDatabricks
 
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch FixThe Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch FixDatabricks
 
Stage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI IntegrationStage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI IntegrationDatabricks
 
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorchSimplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorchDatabricks
 
Scaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on KubernetesScaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on KubernetesDatabricks
 
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark PipelinesScaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark PipelinesDatabricks
 
Sawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature AggregationsSawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature AggregationsDatabricks
 
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen SinkRedis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen SinkDatabricks
 
Re-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and SparkRe-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and SparkDatabricks
 
Raven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction QueriesRaven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction QueriesDatabricks
 
Processing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache SparkProcessing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache SparkDatabricks
 
Massive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta LakeMassive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta LakeDatabricks
 

Plus de Databricks (20)

DW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptxDW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptx
 
Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1
 
Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2
 
Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2
 
Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4
 
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
 
Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized Platform
 
Learn to Use Databricks for Data Science
Learn to Use Databricks for Data ScienceLearn to Use Databricks for Data Science
Learn to Use Databricks for Data Science
 
Why APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML MonitoringWhy APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML Monitoring
 
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch FixThe Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
 
Stage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI IntegrationStage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI Integration
 
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorchSimplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorch
 
Scaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on KubernetesScaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on Kubernetes
 
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark PipelinesScaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
 
Sawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature AggregationsSawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature Aggregations
 
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen SinkRedis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
 
Re-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and SparkRe-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and Spark
 
Raven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction QueriesRaven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction Queries
 
Processing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache SparkProcessing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache Spark
 
Massive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta LakeMassive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta Lake
 

Dernier

Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxolyaivanovalion
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAroojKhan71
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...shambhavirathore45
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
 

Dernier (20)

Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptx
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 

AI-Driven Personalized Email Marketing

  • 2. 2 AI-driven Personalised Marketing Who is Endeavour Group Limited? Endeavour Groups Limited, is Australia’s largest drinks retailer with over 2000 venues across a wide range of brands. The EGL team has built a personalisation marketing engine using Databricks that performs segmentation of EGLs 4.5 million loyalty members. Personalisation is one of most important strategic investments in EGL and is expected to significantly increase revenue and improve customer experience. This session will dive into how EGL has been able to develop effective brand campaigns that target the right people, at the right time with the right messages to millions of their loyalty members. EGL utilizes cutting edge reinforcement learning as a paradigm for Personalization Engine based on data. The Engine elegantly links marketing logics, AI and business processes together, and strives to intelligently determine the balance between the discovery and relevancy of email campaigns.
  • 3. 3 AI-driven Personalised Marketing Topics What problems are we solving? How to use AI to drive personalised marketing? What does our AI solution look like? What are the challenges and how we solved them? Personalised marketing: Who, What When. When to send, what email to use and with what products? We use AI to determine which is the best email template to send a customer Huge data volumes for the model to learn and make predictions We combine reinforcement learning, a recommendation engine and business logic to solve the challenging problem.
  • 4. 4 What problem are we solving Personalised email marketing ● What is the theme of the email? ● What products should be in the email? ● Whom to send the email? ● When to send the email? What are the problems we are solving?
  • 5. Place your image on top of grey square. OR use Layout: 1 Col/Right Image with Image Layout. 5 What problem are we solving … products that the customers are likely to buy, which they have purchased before. What products should we show to who? Past purchase history Demographics XGBoost model Ranks of the likelihood of purchase Buy it again and save!!! Easy!
  • 6. Place your image on top of grey square. OR use Layout: 1 Col/Right Image with Image Layout. 6 What problem are we solving You have bought this ... Why not try this … ? … products that the customers are likely to buy, which they have NOT purchased before. What products should we show to who? Past purchases Products attributes XGBoost Ranks of the likelihood of purchase Marketing response Seasonality Harder!
  • 7. Place your image on top of grey square. OR use Layout: 1 Col/Right Image with Image Layout. 7 What problem are we solving … 3 out of 2000 emails that you are more likely to click and then buy What is the theme of the email? Past purchases Products attributes Multi-armed bandit Likelihood of click + buy the product in the email Marketing response Email attributes Hardest!
  • 8. Place your image on top of grey square. OR use Layout: 1 Col/Right Image with Image Layout. 8 What problem are we solving What time should we send the email Easy! No AI yet.. … just pick 35 random time slots in a week! The next step is to use AI to identify the time slots and frequency that customers will click and buy the product … … and will not lead to unsubscribe!
  • 9. 9 There are three key components in our Personalisation
  • 10. Email Examples - Mega-Intro + Christmas Content relevance -> previously purchased generic discovery_seg -> recommended—single category discovery -> recommended—cross category
  • 11. 11
  • 12. 12 Let’s get into the nitty-gritty technical details!
  • 13. 13 How does our AI solution look like? Thompson algorithm We structure the email selection as an multi-armed bandit problem and use Thompson algorithm as the solution. We model it as a Multi-Armed Bandit (MAB problem Bandit 70% Current success rate Bandit 30% Current success rate Bandit 50% Current success rate Next choice? Decision making MAB Optimisation Choose the best product By finding the best emails Minimise the total regrets By avoiding sending bad emails as much as possible
  • 14. 14 What are the challenges and how to solve them It was a tough decision between cold start v.s. warm start
  • 16. 16 How does our AI solution look like? … we have to wait and see It was not easy to balance between exploration and exploitation for a multi-armed bandit problem...
  • 17. 17 What are the challenges and how to solve them Algorithms and technologies are just parts of the puzzle, there are many business processes need to be considered or adjusted. ● There are some time sensitive emails which we want to send more of it in a short amount of time, e.g. Easter. We upweight those actions so they get higher rankings. The upweight is chosen in a way to minimize the clicks lost whilst getting our desired amount of sends. Additional email sent Upweight level
  • 18. 18 What are the challenges and how to solve them Algorithms and technologies are just parts of the puzzle, there are many business processes need to be considered or adjusted. Are we sending too many emails that cause unsubscription? Do we send the same emails over and over again? How do we bring customers to a pleasant journey, e.g. onboarding How can we treat a cohort differently if the incremental sales are not the focus, e.g. retention How can we deliver consistent messages across all channels? How do we choose emails that a model has never seen before?
  • 19. AI-driven Personalised Marketing What’s next in the EGL personalisation Journey Personalised landing page Personalised searching results Personalised customer review Personalised basket building Personalised customer retention Personalised journey Personalised App push notifications Personalised offer 19