SlideShare a Scribd company logo
1 of 17
Why maintaining ml in production is so hard?
● Models start to constantly degrade the moment they are used in production
● Model errors become clear only in the future, often after decision was made based on
prediction
Agenda
● MLOps engineering, monitoring
● Real world example, some good
practices
MLOps engineering
MLOps engineering
● Infrastructure
● CI/CD/ML Pipelines
● Automation
● Monitoring
● Trusting your predictions
Metric is the key
● Finding good metric is hard
● Some baseline is required
● Measure what matters
Accuracy
● Depends on the use case
● Typical metrics: RMSE, LogLoss, Confusion matrix metrics and many others
● Sometimes we might not care about accuracy that much
● Can only be measured after actual value is known
Data Drift
● Can be measured even before predictions are made
○ Pro tip: mark outliers for investigation
● Typical metrics: PSI, Kolmogorov-Smirnov, Jensen-Shannon
● It might be hard to monitor all features
○ It is a good idea to limit only to “important” features
Covid 19
Covid 19
Solving covid 19 is extremely hard
● ~3000 different “independent” geographical locations in US
● Forecasts need to go into the far future (>12 weeks)
● World changes daily
○ New policies, new strains, vaccines, population behavior, …
Operational complexity
● ~30 data sources collected daily
○ new cases/deaths, population mobility, vaccine distribution, etc
● Results are required daily
● Full pipeline run ~8 hours
Data itself is a part of the software
Treat data same way you treat code
● Tests for the data
○ Number of new cases > 0
● Versioning
○ semantic versions, every job knows which versions it required and produces
● Backups
○ Delete nothing, just offload to storage
What else helped us
● “Trust” checks
○ data/model/sanity/metric checks
● Constant backtesting
● Fine tuning and manual approvals
● Daily retraining
○ If we have all the monitoring and checks, why not?
Thanks for attention

More Related Content

Similar to "ML in Production",Oleksandr Bagan

The Machine Learning Audit
The Machine Learning AuditThe Machine Learning Audit
The Machine Learning AuditAndrew Clark
 
Anomaly detection made easy - Piotr Guzik Allegro
Anomaly detection made easy - Piotr Guzik AllegroAnomaly detection made easy - Piotr Guzik Allegro
Anomaly detection made easy - Piotr Guzik AllegroEvention
 
Anomaly detection made easy
Anomaly detection made easyAnomaly detection made easy
Anomaly detection made easyPiotr Guzik
 
Production-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to heroProduction-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to heroDaniel Marcous
 
"What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual..."What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual...Dataconomy Media
 
Mortal analytics - Covid-19 and the problem of data quality
Mortal analytics - Covid-19 and the problem of data qualityMortal analytics - Covid-19 and the problem of data quality
Mortal analytics - Covid-19 and the problem of data qualityLars Albertsson
 
Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0Albert Y. C. Chen
 
Break Up the Monolith- Testing Microservices by Marcus Merrell
Break Up the Monolith- Testing Microservices by Marcus MerrellBreak Up the Monolith- Testing Microservices by Marcus Merrell
Break Up the Monolith- Testing Microservices by Marcus MerrellSauce Labs
 
[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic
[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic
[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes DeumicDataScienceConferenc1
 
AI hype or reality
AI  hype or realityAI  hype or reality
AI hype or realityAwantik Das
 
CISSP Week 12
CISSP Week 12CISSP Week 12
CISSP Week 12jemtallon
 
Live predictions with schemaless data at scale. MLMU Kosice, Exponea
Live predictions with schemaless data at scale. MLMU Kosice, ExponeaLive predictions with schemaless data at scale. MLMU Kosice, Exponea
Live predictions with schemaless data at scale. MLMU Kosice, ExponeaData Science Club
 
Lessons learned from designing a QA Automation for analytics databases (big d...
Lessons learned from designing a QA Automation for analytics databases (big d...Lessons learned from designing a QA Automation for analytics databases (big d...
Lessons learned from designing a QA Automation for analytics databases (big d...Omid Vahdaty
 
CD in Machine Learning Systems
CD in Machine Learning SystemsCD in Machine Learning Systems
CD in Machine Learning SystemsThoughtworks
 
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...Maximize Your Understanding of Operational Realities in Manufacturing with Pr...
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...Bigfinite
 
PyData Global 2022 - Things I learned while running neural networks on microc...
PyData Global 2022 - Things I learned while running neural networks on microc...PyData Global 2022 - Things I learned while running neural networks on microc...
PyData Global 2022 - Things I learned while running neural networks on microc...SARADINDU SENGUPTA
 

Similar to "ML in Production",Oleksandr Bagan (20)

The Machine Learning Audit
The Machine Learning AuditThe Machine Learning Audit
The Machine Learning Audit
 
Anomaly detection made easy - Piotr Guzik Allegro
Anomaly detection made easy - Piotr Guzik AllegroAnomaly detection made easy - Piotr Guzik Allegro
Anomaly detection made easy - Piotr Guzik Allegro
 
Anomaly detection made easy
Anomaly detection made easyAnomaly detection made easy
Anomaly detection made easy
 
C2_W1---.pdf
C2_W1---.pdfC2_W1---.pdf
C2_W1---.pdf
 
Production-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to heroProduction-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to hero
 
"What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual..."What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual...
 
Data preprocessing.pdf
Data preprocessing.pdfData preprocessing.pdf
Data preprocessing.pdf
 
Data science guide
Data science guideData science guide
Data science guide
 
Mortal analytics - Covid-19 and the problem of data quality
Mortal analytics - Covid-19 and the problem of data qualityMortal analytics - Covid-19 and the problem of data quality
Mortal analytics - Covid-19 and the problem of data quality
 
Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0
 
Sea of Data
Sea of DataSea of Data
Sea of Data
 
Break Up the Monolith- Testing Microservices by Marcus Merrell
Break Up the Monolith- Testing Microservices by Marcus MerrellBreak Up the Monolith- Testing Microservices by Marcus Merrell
Break Up the Monolith- Testing Microservices by Marcus Merrell
 
[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic
[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic
[DSC Croatia 22] Modeling the Dynamics of User Engagement - Enes Deumic
 
AI hype or reality
AI  hype or realityAI  hype or reality
AI hype or reality
 
CISSP Week 12
CISSP Week 12CISSP Week 12
CISSP Week 12
 
Live predictions with schemaless data at scale. MLMU Kosice, Exponea
Live predictions with schemaless data at scale. MLMU Kosice, ExponeaLive predictions with schemaless data at scale. MLMU Kosice, Exponea
Live predictions with schemaless data at scale. MLMU Kosice, Exponea
 
Lessons learned from designing a QA Automation for analytics databases (big d...
Lessons learned from designing a QA Automation for analytics databases (big d...Lessons learned from designing a QA Automation for analytics databases (big d...
Lessons learned from designing a QA Automation for analytics databases (big d...
 
CD in Machine Learning Systems
CD in Machine Learning SystemsCD in Machine Learning Systems
CD in Machine Learning Systems
 
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...Maximize Your Understanding of Operational Realities in Manufacturing with Pr...
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...
 
PyData Global 2022 - Things I learned while running neural networks on microc...
PyData Global 2022 - Things I learned while running neural networks on microc...PyData Global 2022 - Things I learned while running neural networks on microc...
PyData Global 2022 - Things I learned while running neural networks on microc...
 

More from Fwdays

"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y..."How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...Fwdays
 
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil TopchiiFwdays
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro Spodarets"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro SpodaretsFwdays
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
"Distributed graphs and microservices in Prom.ua", Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua", Maksym KindritskyiFwdays
 
"Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl..."Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl...Fwdays
 
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T..."How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...Fwdays
 
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ..."The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...Fwdays
 
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu..."[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...Fwdays
 
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care..."[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...Fwdays
 
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"..."4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...Fwdays
 
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast..."Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...Fwdays
 
"Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others..."Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others...Fwdays
 
"Mission (im) possible: How to get an offer in 2024?", Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?", Oleksandra MyronovaFwdays
 
"Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv..."Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv...Fwdays
 
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin..."How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...Fwdays
 
"Leadership, Soft Skills, and Personality Types for IT teams", Sergiy Tytenko
"Leadership, Soft Skills, and Personality Types for IT teams",  Sergiy Tytenko"Leadership, Soft Skills, and Personality Types for IT teams",  Sergiy Tytenko
"Leadership, Soft Skills, and Personality Types for IT teams", Sergiy TytenkoFwdays
 

More from Fwdays (20)

"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y..."How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
 
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro Spodarets"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro Spodarets
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
"Distributed graphs and microservices in Prom.ua", Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua", Maksym Kindritskyi
 
"Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl..."Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl...
 
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T..."How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...
 
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ..."The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
 
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu..."[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
 
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care..."[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
 
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"..."4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
 
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast..."Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...
 
"Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others..."Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others...
 
"Mission (im) possible: How to get an offer in 2024?", Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?", Oleksandra Myronova
 
"Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv..."Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv...
 
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin..."How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
 
"Leadership, Soft Skills, and Personality Types for IT teams", Sergiy Tytenko
"Leadership, Soft Skills, and Personality Types for IT teams",  Sergiy Tytenko"Leadership, Soft Skills, and Personality Types for IT teams",  Sergiy Tytenko
"Leadership, Soft Skills, and Personality Types for IT teams", Sergiy Tytenko
 

Recently uploaded

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 

Recently uploaded (20)

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 

"ML in Production",Oleksandr Bagan

  • 1.
  • 2.
  • 3. Why maintaining ml in production is so hard? ● Models start to constantly degrade the moment they are used in production ● Model errors become clear only in the future, often after decision was made based on prediction
  • 4. Agenda ● MLOps engineering, monitoring ● Real world example, some good practices
  • 6. MLOps engineering ● Infrastructure ● CI/CD/ML Pipelines ● Automation ● Monitoring ● Trusting your predictions
  • 7. Metric is the key ● Finding good metric is hard ● Some baseline is required ● Measure what matters
  • 8. Accuracy ● Depends on the use case ● Typical metrics: RMSE, LogLoss, Confusion matrix metrics and many others ● Sometimes we might not care about accuracy that much ● Can only be measured after actual value is known
  • 9. Data Drift ● Can be measured even before predictions are made ○ Pro tip: mark outliers for investigation ● Typical metrics: PSI, Kolmogorov-Smirnov, Jensen-Shannon ● It might be hard to monitor all features ○ It is a good idea to limit only to “important” features
  • 12. Solving covid 19 is extremely hard ● ~3000 different “independent” geographical locations in US ● Forecasts need to go into the far future (>12 weeks) ● World changes daily ○ New policies, new strains, vaccines, population behavior, …
  • 13. Operational complexity ● ~30 data sources collected daily ○ new cases/deaths, population mobility, vaccine distribution, etc ● Results are required daily ● Full pipeline run ~8 hours
  • 14. Data itself is a part of the software
  • 15. Treat data same way you treat code ● Tests for the data ○ Number of new cases > 0 ● Versioning ○ semantic versions, every job knows which versions it required and produces ● Backups ○ Delete nothing, just offload to storage
  • 16. What else helped us ● “Trust” checks ○ data/model/sanity/metric checks ● Constant backtesting ● Fine tuning and manual approvals ● Daily retraining ○ If we have all the monitoring and checks, why not?