SlideShare une entreprise Scribd logo
1  sur  28
Bringing ML to Production,
what is missing?
Mikio Braun, Staff Data Scientist
Applied ML Days, Lausanne 2020
With thousands of incredible experiences around the world, GetYourGuide is at the
heart of travel
Applied ML Days, Lausanne 2020
We’ve built one of the world’s biggest marketplace 

for travel activities…
Millions of travelers use 

GetYourGuide every year
We facilitate the transaction We offer more than 40,000 

activities worldwide
Connecting 

customers...
...to suppliers 

around the world
Applied ML Days, Lausanne 2020
Hop-on hop-off Attractions Outdoor activities
TransfersAmusement parksCooking classesWalking tours
Applied ML Days, Lausanne 2020
So How Do You “Do AI?”
https://hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007
What is there beyond algorithms and tools?
● Figuring out where to apply ML
● Architecting ML applications
● Teams & Organizations
Business Problems to ML Problems
Applied ML Days, Lausanne 2020
GetYourGuide Overview
Applied ML Days, Lausanne 2020
GetYourGuide Overview
Applied ML Days, Lausanne 2020
From Business Problems To Machine Learning Problems
• Customer has a Job to be
done.
• Business has to give a
Solution that adds value.
• Solution consists of Activities,
and some of that activities
might be solved with ML.
• ML: solve a task by learning
from examples.
Applied ML Days, Lausanne 2020
Machine Learning: Learn From Examples
Applied ML Days, Lausanne 2020
Example: Recommendations
Applied ML Days, Lausanne 2020
Typical problem for machine learning:
• Hard to specify what exactly
means “similar.”
• A lot of example data is
available.
• Recommendations have to
change based on new articles
frequently.
Example: Recommendations
Applied ML Days, Lausanne 2020
• Business/customer view and
machine learning view often
have different metrics.
• Machine learning does not
know about the business
view.
• Figuring out the right
relationship is not easy.
• Also depends on the
available data.
Example: Recommendation
Applied ML Days, Lausanne 2020
Architectures for AI Systems
Applied ML Days, Lausanne 2020
Machine Learning Systems
Applied ML Days, Lausanne 2020
Design Patterns for AI Architectures
Core Machine Learning

—how to train, evaluate, etc.
Serving

—access predictions in real-time
Data Preprocessing and Features

—how to deal with preprocessing
Automation & Monitoring

—making it more production
ready
Machine Learning Integration

—how to fit it into a larger picture
Applied ML Days, Lausanne 2020
Machine Learning Integration Patterns
• Depending on how ML
is used, there are
different integration
patterns.
• Keep in mind that the
ML problem and the
application problem
are different and have
different metrics.
• Beware of interacting
ML models if the overall
training data is used.
Applied ML Days, Lausanne 2020
Serving Patterns
•How to provide the predictions of the machine learning model to the application.
•If the domain is small, precomputing predictions might be the easiest way to serve.
Applied ML Days, Lausanne 2020
Preprocessing Patterns
• If predictions are
precomputed, no
special treatment of
feature computation
is necessary.
• If it is served online,
you can either
precompute features
in a Feature Store. But
you don’t have
updates for new data.
• Or you can use the
Feature Store and
update features
online as well.
Applied ML Days, Lausanne 2020
Teams and Organization
How Data Scientists Work
Applied ML Days, Lausanne 2020
Data Scientists And Developers
Applied ML Days, Lausanne 2020
Data Scientists and Developers Collaboration
• What is the most
productive way?
• Ideally, interface on
code, not just
documentation
• Production logs often
become data analysis
input!
Applied ML Days, Lausanne 2020
Organizing Data Science
Applied ML Days, Lausanne 2020
Data Platforms
https://hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007
Applied ML Days, Lausanne 2020
Machine Learning: The High Interest Credit Card of Technical
Debt
Summary
● Not just about methods and tools.
● How to identify where to use ML?
● Building AI/ML systems.
● How to set up teams and
organizations for ML.
Questions?
mikio.braun@getyourguide.com
Twitter @mikiobraun

Contenu connexe

Tendances

Apply MLOps at Scale
Apply MLOps at ScaleApply MLOps at Scale
Apply MLOps at ScaleDatabricks
 
Feature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine LearningFeature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine LearningProvectus
 
Generative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptxGenerative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptxColleen Farrelly
 
Landscape of AI/ML in 2023
Landscape of AI/ML in 2023Landscape of AI/ML in 2023
Landscape of AI/ML in 2023HyunJoon Jung
 
Architecting Agile Data Applications for Scale
Architecting Agile Data Applications for ScaleArchitecting Agile Data Applications for Scale
Architecting Agile Data Applications for ScaleDatabricks
 
Introdution to Dataops and AIOps (or MLOps)
Introdution to Dataops and AIOps (or MLOps)Introdution to Dataops and AIOps (or MLOps)
Introdution to Dataops and AIOps (or MLOps)Adrien Blind
 
Machine Learning using Kubeflow and Kubernetes
Machine Learning using Kubeflow and KubernetesMachine Learning using Kubeflow and Kubernetes
Machine Learning using Kubeflow and KubernetesArun Gupta
 
Holland & Barrett: Gen AI Prompt Engineering for Tech teams
Holland & Barrett: Gen AI Prompt Engineering for Tech teamsHolland & Barrett: Gen AI Prompt Engineering for Tech teams
Holland & Barrett: Gen AI Prompt Engineering for Tech teamsDobo Radichkov
 
Generative AI at the edge.pdf
Generative AI at the edge.pdfGenerative AI at the edge.pdf
Generative AI at the edge.pdfQualcomm Research
 
Conversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsCristina Vidu
 
Introduction to Knowledge Graphs and Semantic AI
Introduction to Knowledge Graphs and Semantic AIIntroduction to Knowledge Graphs and Semantic AI
Introduction to Knowledge Graphs and Semantic AISemantic Web Company
 
An Introduction to Generative AI
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AICori Faklaris
 
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1DianaGray10
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflowDatabricks
 
How ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyHow ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyPekka Abrahamsson / Tampere University
 
Databricks Overview for MLOps
Databricks Overview for MLOpsDatabricks Overview for MLOps
Databricks Overview for MLOpsDatabricks
 
Mlflow with databricks
Mlflow with databricksMlflow with databricks
Mlflow with databricksLiangjun Jiang
 
Prompt Engineering - an Art, a Science, or your next Job Title?
Prompt Engineering - an Art, a Science, or your next Job Title?Prompt Engineering - an Art, a Science, or your next Job Title?
Prompt Engineering - an Art, a Science, or your next Job Title?Maxim Salnikov
 

Tendances (20)

Apply MLOps at Scale
Apply MLOps at ScaleApply MLOps at Scale
Apply MLOps at Scale
 
Feature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine LearningFeature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine Learning
 
Generative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptxGenerative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptx
 
Landscape of AI/ML in 2023
Landscape of AI/ML in 2023Landscape of AI/ML in 2023
Landscape of AI/ML in 2023
 
MLOps in action
MLOps in actionMLOps in action
MLOps in action
 
Architecting Agile Data Applications for Scale
Architecting Agile Data Applications for ScaleArchitecting Agile Data Applications for Scale
Architecting Agile Data Applications for Scale
 
LLMs Bootcamp
LLMs BootcampLLMs Bootcamp
LLMs Bootcamp
 
Introdution to Dataops and AIOps (or MLOps)
Introdution to Dataops and AIOps (or MLOps)Introdution to Dataops and AIOps (or MLOps)
Introdution to Dataops and AIOps (or MLOps)
 
Machine Learning using Kubeflow and Kubernetes
Machine Learning using Kubeflow and KubernetesMachine Learning using Kubeflow and Kubernetes
Machine Learning using Kubeflow and Kubernetes
 
Holland & Barrett: Gen AI Prompt Engineering for Tech teams
Holland & Barrett: Gen AI Prompt Engineering for Tech teamsHolland & Barrett: Gen AI Prompt Engineering for Tech teams
Holland & Barrett: Gen AI Prompt Engineering for Tech teams
 
Generative AI at the edge.pdf
Generative AI at the edge.pdfGenerative AI at the edge.pdf
Generative AI at the edge.pdf
 
Conversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot Integrations
 
Introduction to Knowledge Graphs and Semantic AI
Introduction to Knowledge Graphs and Semantic AIIntroduction to Knowledge Graphs and Semantic AI
Introduction to Knowledge Graphs and Semantic AI
 
An Introduction to Generative AI
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AI
 
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflow
 
How ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyHow ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundly
 
Databricks Overview for MLOps
Databricks Overview for MLOpsDatabricks Overview for MLOps
Databricks Overview for MLOps
 
Mlflow with databricks
Mlflow with databricksMlflow with databricks
Mlflow with databricks
 
Prompt Engineering - an Art, a Science, or your next Job Title?
Prompt Engineering - an Art, a Science, or your next Job Title?Prompt Engineering - an Art, a Science, or your next Job Title?
Prompt Engineering - an Art, a Science, or your next Job Title?
 

Similaire à Bringing ML To Production, What Is Missing? AMLD 2020

CIO Leadership Summit 2018 - From Digital to Intelligent Enterprise
CIO Leadership Summit 2018 - From Digital to Intelligent EnterpriseCIO Leadership Summit 2018 - From Digital to Intelligent Enterprise
CIO Leadership Summit 2018 - From Digital to Intelligent EnterprisePhilippe Nemery
 
Reading the IBM AI Strategy for Business
Reading the IBM AI Strategy for BusinessReading the IBM AI Strategy for Business
Reading the IBM AI Strategy for BusinessPietro Leo
 
SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...
SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...
SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...NUS-ISS
 
IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era.  IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era. Benoit Marolleau
 
Ganintegrate- Think Smart Integration brochure
Ganintegrate- Think Smart Integration brochure Ganintegrate- Think Smart Integration brochure
Ganintegrate- Think Smart Integration brochure Judith Mugeni
 
Perform data annotation for quality workforce management
Perform data annotation for quality workforce managementPerform data annotation for quality workforce management
Perform data annotation for quality workforce managementAnnotation World
 
AI for Customer Service - How to Improve Contact Center Efficiency with Machi...
AI for Customer Service - How to Improve Contact Center Efficiency with Machi...AI for Customer Service - How to Improve Contact Center Efficiency with Machi...
AI for Customer Service - How to Improve Contact Center Efficiency with Machi...Skyl.ai
 
Architecting AI Applications
Architecting AI ApplicationsArchitecting AI Applications
Architecting AI ApplicationsMikio L. Braun
 
David Braun. Scaling service business. Is it possible?
David Braun. Scaling service business. Is it possible?David Braun. Scaling service business. Is it possible?
David Braun. Scaling service business. Is it possible?IT Arena
 
Tableau 2018 - Introduction to Visual analytics
Tableau 2018 - Introduction to Visual analyticsTableau 2018 - Introduction to Visual analytics
Tableau 2018 - Introduction to Visual analyticsArun K
 
Top 10 Skills You Need For A High-Paying Machine Learning Career
Top 10 Skills You Need For A High-Paying Machine Learning CareerTop 10 Skills You Need For A High-Paying Machine Learning Career
Top 10 Skills You Need For A High-Paying Machine Learning CareerRobert Smith
 
Business intelligence solutions english
Business intelligence solutions englishBusiness intelligence solutions english
Business intelligence solutions englishStratebi
 
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB
 
Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...
Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...
Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...Data Con LA
 
Machine learning for product development
Machine learning for product developmentMachine learning for product development
Machine learning for product developmentClaudio Villar
 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineMongoDB
 
Top Business Intelligence Trends for 2016 by Panorama Software
Top Business Intelligence Trends for 2016 by Panorama SoftwareTop Business Intelligence Trends for 2016 by Panorama Software
Top Business Intelligence Trends for 2016 by Panorama SoftwarePanorama Software
 

Similaire à Bringing ML To Production, What Is Missing? AMLD 2020 (20)

CIO Leadership Summit 2018 - From Digital to Intelligent Enterprise
CIO Leadership Summit 2018 - From Digital to Intelligent EnterpriseCIO Leadership Summit 2018 - From Digital to Intelligent Enterprise
CIO Leadership Summit 2018 - From Digital to Intelligent Enterprise
 
Reading the IBM AI Strategy for Business
Reading the IBM AI Strategy for BusinessReading the IBM AI Strategy for Business
Reading the IBM AI Strategy for Business
 
SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...
SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...
SkillsFuture Festival at NUS 2019- Artificial Intelligence for Everyone - A P...
 
IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era.  IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era.
 
Salesforce Einstein: Use Cases and Product Features
Salesforce Einstein: Use Cases and Product FeaturesSalesforce Einstein: Use Cases and Product Features
Salesforce Einstein: Use Cases and Product Features
 
Ganintegrate- Think Smart Integration brochure
Ganintegrate- Think Smart Integration brochure Ganintegrate- Think Smart Integration brochure
Ganintegrate- Think Smart Integration brochure
 
Perform data annotation for quality workforce management
Perform data annotation for quality workforce managementPerform data annotation for quality workforce management
Perform data annotation for quality workforce management
 
AI for Customer Service - How to Improve Contact Center Efficiency with Machi...
AI for Customer Service - How to Improve Contact Center Efficiency with Machi...AI for Customer Service - How to Improve Contact Center Efficiency with Machi...
AI for Customer Service - How to Improve Contact Center Efficiency with Machi...
 
Architecting AI Applications
Architecting AI ApplicationsArchitecting AI Applications
Architecting AI Applications
 
Resume Boubaker Abdallah
Resume Boubaker AbdallahResume Boubaker Abdallah
Resume Boubaker Abdallah
 
David Braun. Scaling service business. Is it possible?
David Braun. Scaling service business. Is it possible?David Braun. Scaling service business. Is it possible?
David Braun. Scaling service business. Is it possible?
 
Tableau 2018 - Introduction to Visual analytics
Tableau 2018 - Introduction to Visual analyticsTableau 2018 - Introduction to Visual analytics
Tableau 2018 - Introduction to Visual analytics
 
Top 10 Skills You Need For A High-Paying Machine Learning Career
Top 10 Skills You Need For A High-Paying Machine Learning CareerTop 10 Skills You Need For A High-Paying Machine Learning Career
Top 10 Skills You Need For A High-Paying Machine Learning Career
 
Business intelligence solutions english
Business intelligence solutions englishBusiness intelligence solutions english
Business intelligence solutions english
 
Mappe e algoritmi
Mappe e algoritmi Mappe e algoritmi
Mappe e algoritmi
 
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
 
Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...
Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...
Data Con LA 2022 - Demystifying the Art of Business Intelligence and Data Ana...
 
Machine learning for product development
Machine learning for product developmentMachine learning for product development
Machine learning for product development
 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
 
Top Business Intelligence Trends for 2016 by Panorama Software
Top Business Intelligence Trends for 2016 by Panorama SoftwareTop Business Intelligence Trends for 2016 by Panorama Software
Top Business Intelligence Trends for 2016 by Panorama Software
 

Plus de Mikio L. Braun

Academia to industry looking back on a decade of ml
Academia to industry looking back on a decade of mlAcademia to industry looking back on a decade of ml
Academia to industry looking back on a decade of mlMikio L. Braun
 
Machine Learning for Time Series, Strata London 2018
Machine Learning for Time Series, Strata London 2018Machine Learning for Time Series, Strata London 2018
Machine Learning for Time Series, Strata London 2018Mikio L. Braun
 
Hardcore Data Science - in Practice
Hardcore Data Science - in PracticeHardcore Data Science - in Practice
Hardcore Data Science - in PracticeMikio L. Braun
 
Data flow vs. procedural programming: How to put your algorithms into Flink
Data flow vs. procedural programming: How to put your algorithms into FlinkData flow vs. procedural programming: How to put your algorithms into Flink
Data flow vs. procedural programming: How to put your algorithms into FlinkMikio L. Braun
 
Scalable Machine Learning
Scalable Machine LearningScalable Machine Learning
Scalable Machine LearningMikio L. Braun
 
Realtime Data Analysis Patterns
Realtime Data Analysis PatternsRealtime Data Analysis Patterns
Realtime Data Analysis PatternsMikio L. Braun
 
Cassandra - An Introduction
Cassandra - An IntroductionCassandra - An Introduction
Cassandra - An IntroductionMikio L. Braun
 
Cassandra - Eine Einführung
Cassandra - Eine EinführungCassandra - Eine Einführung
Cassandra - Eine EinführungMikio L. Braun
 

Plus de Mikio L. Braun (8)

Academia to industry looking back on a decade of ml
Academia to industry looking back on a decade of mlAcademia to industry looking back on a decade of ml
Academia to industry looking back on a decade of ml
 
Machine Learning for Time Series, Strata London 2018
Machine Learning for Time Series, Strata London 2018Machine Learning for Time Series, Strata London 2018
Machine Learning for Time Series, Strata London 2018
 
Hardcore Data Science - in Practice
Hardcore Data Science - in PracticeHardcore Data Science - in Practice
Hardcore Data Science - in Practice
 
Data flow vs. procedural programming: How to put your algorithms into Flink
Data flow vs. procedural programming: How to put your algorithms into FlinkData flow vs. procedural programming: How to put your algorithms into Flink
Data flow vs. procedural programming: How to put your algorithms into Flink
 
Scalable Machine Learning
Scalable Machine LearningScalable Machine Learning
Scalable Machine Learning
 
Realtime Data Analysis Patterns
Realtime Data Analysis PatternsRealtime Data Analysis Patterns
Realtime Data Analysis Patterns
 
Cassandra - An Introduction
Cassandra - An IntroductionCassandra - An Introduction
Cassandra - An Introduction
 
Cassandra - Eine Einführung
Cassandra - Eine EinführungCassandra - Eine Einführung
Cassandra - Eine Einführung
 

Dernier

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
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 WorkerThousandEyes
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdfChristopherTHyatt
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 

Dernier (20)

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
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
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdf
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 

Bringing ML To Production, What Is Missing? AMLD 2020

  • 1. Bringing ML to Production, what is missing? Mikio Braun, Staff Data Scientist Applied ML Days, Lausanne 2020
  • 2. With thousands of incredible experiences around the world, GetYourGuide is at the heart of travel Applied ML Days, Lausanne 2020
  • 3. We’ve built one of the world’s biggest marketplace 
 for travel activities… Millions of travelers use 
 GetYourGuide every year We facilitate the transaction We offer more than 40,000 
 activities worldwide Connecting 
 customers... ...to suppliers 
 around the world Applied ML Days, Lausanne 2020
  • 4. Hop-on hop-off Attractions Outdoor activities TransfersAmusement parksCooking classesWalking tours Applied ML Days, Lausanne 2020
  • 5. So How Do You “Do AI?” https://hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007
  • 6. What is there beyond algorithms and tools? ● Figuring out where to apply ML ● Architecting ML applications ● Teams & Organizations
  • 7. Business Problems to ML Problems Applied ML Days, Lausanne 2020
  • 8. GetYourGuide Overview Applied ML Days, Lausanne 2020
  • 9. GetYourGuide Overview Applied ML Days, Lausanne 2020
  • 10. From Business Problems To Machine Learning Problems • Customer has a Job to be done. • Business has to give a Solution that adds value. • Solution consists of Activities, and some of that activities might be solved with ML. • ML: solve a task by learning from examples. Applied ML Days, Lausanne 2020
  • 11. Machine Learning: Learn From Examples Applied ML Days, Lausanne 2020
  • 12. Example: Recommendations Applied ML Days, Lausanne 2020
  • 13. Typical problem for machine learning: • Hard to specify what exactly means “similar.” • A lot of example data is available. • Recommendations have to change based on new articles frequently. Example: Recommendations Applied ML Days, Lausanne 2020
  • 14. • Business/customer view and machine learning view often have different metrics. • Machine learning does not know about the business view. • Figuring out the right relationship is not easy. • Also depends on the available data. Example: Recommendation Applied ML Days, Lausanne 2020
  • 15. Architectures for AI Systems Applied ML Days, Lausanne 2020
  • 16. Machine Learning Systems Applied ML Days, Lausanne 2020
  • 17. Design Patterns for AI Architectures Core Machine Learning
 —how to train, evaluate, etc. Serving
 —access predictions in real-time Data Preprocessing and Features
 —how to deal with preprocessing Automation & Monitoring
 —making it more production ready Machine Learning Integration
 —how to fit it into a larger picture Applied ML Days, Lausanne 2020
  • 18. Machine Learning Integration Patterns • Depending on how ML is used, there are different integration patterns. • Keep in mind that the ML problem and the application problem are different and have different metrics. • Beware of interacting ML models if the overall training data is used. Applied ML Days, Lausanne 2020
  • 19. Serving Patterns •How to provide the predictions of the machine learning model to the application. •If the domain is small, precomputing predictions might be the easiest way to serve. Applied ML Days, Lausanne 2020
  • 20. Preprocessing Patterns • If predictions are precomputed, no special treatment of feature computation is necessary. • If it is served online, you can either precompute features in a Feature Store. But you don’t have updates for new data. • Or you can use the Feature Store and update features online as well. Applied ML Days, Lausanne 2020
  • 22. How Data Scientists Work Applied ML Days, Lausanne 2020
  • 23. Data Scientists And Developers Applied ML Days, Lausanne 2020
  • 24. Data Scientists and Developers Collaboration • What is the most productive way? • Ideally, interface on code, not just documentation • Production logs often become data analysis input! Applied ML Days, Lausanne 2020
  • 25. Organizing Data Science Applied ML Days, Lausanne 2020
  • 26. Data Platforms https://hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007 Applied ML Days, Lausanne 2020 Machine Learning: The High Interest Credit Card of Technical Debt
  • 27. Summary ● Not just about methods and tools. ● How to identify where to use ML? ● Building AI/ML systems. ● How to set up teams and organizations for ML.