Machine Learning from Development to Production at Instacart | Instacart
Get the slides: https://www.datacouncil.ai/talks/machine-learning-from-development-to-production-at-instacart?utm_source=youtube&utm_medium=social&utm_campaign=%20-%20DEC-SF-18%20Slides%20Download
ABOUT THE TALK:
As Instacart has grown from a single data scientist building linear models, to multiple teams building and maintaining dozens of bespoke models, to a more mature organization collaborating across multiple fields, we’ve learned a few things the hard way. We’re open sourcing our solutions as Lore.
Common Problems:
1. Information overload makes it easy to miss newly available low hanging fruit when trying to keep up with all the machine learning packages, their features, nuances and bugs — much less implementing the latest from academia.
2. Complexity grows because valuable models are the result of many iterative insights, making individual insights harder to maintain and communicate.
3. Repeatability is non trivial when code, data and library dependencies change constantly in modern environments. Especially when someone else wrote the original, years ago.
4. Glue code is often mundane and tedious to write. It’s a frequent source of bugs because there is much to write, more to maintain, and all of it has low mind-share.
5. Performance bottlenecks are easy to hit when you’re working at high levels like python or SQL.
Our goal is to make machine learning approachable for Engineers and maintainable for Data Scientists. There are a lot of great libraries like numpy, pandas, scikit, tensorflow, xgboost, etc. that work together in our daily workflow. Lore is our codification of best practices that welds the valuable bits seamlessly into production models. We're open sourcing so we can learn from the community as well.
ABOUT THE SPEAKER:
Montana works as a Machine Learning Engineer with a diverse team at Instacart to drive growth, reduce costs, and ensure they can reliably deliver the core product: your groceries, in an hour. He has also been the Chief Scientist at RescueTime and founder of two other startups that used machine learning to differentiate their apps.
ABOUT DATA COUNCIL:
Data Council (https://www.datacouncil.ai/) is a community and conference series that provides data professionals with the learning and networking opportunities they need to grow their careers. Make sure to subscribe to our channel for more videos, including DC_THURS, our series of live online interviews with leading data professionals from top open source projects and startups.
FOLLOW DATA COUNCIL:
Twitter: https://twitter.com/DataCouncilAI
LinkedIn: https://www.linkedin.com/company/datacouncil-ai
Facebook: https://www.facebook.com/datacouncilai
Eventbrite: https://www.eventbrite.com/o/data-council-30357384520
Видео Machine Learning from Development to Production at Instacart | Instacart канала Data Council
ABOUT THE TALK:
As Instacart has grown from a single data scientist building linear models, to multiple teams building and maintaining dozens of bespoke models, to a more mature organization collaborating across multiple fields, we’ve learned a few things the hard way. We’re open sourcing our solutions as Lore.
Common Problems:
1. Information overload makes it easy to miss newly available low hanging fruit when trying to keep up with all the machine learning packages, their features, nuances and bugs — much less implementing the latest from academia.
2. Complexity grows because valuable models are the result of many iterative insights, making individual insights harder to maintain and communicate.
3. Repeatability is non trivial when code, data and library dependencies change constantly in modern environments. Especially when someone else wrote the original, years ago.
4. Glue code is often mundane and tedious to write. It’s a frequent source of bugs because there is much to write, more to maintain, and all of it has low mind-share.
5. Performance bottlenecks are easy to hit when you’re working at high levels like python or SQL.
Our goal is to make machine learning approachable for Engineers and maintainable for Data Scientists. There are a lot of great libraries like numpy, pandas, scikit, tensorflow, xgboost, etc. that work together in our daily workflow. Lore is our codification of best practices that welds the valuable bits seamlessly into production models. We're open sourcing so we can learn from the community as well.
ABOUT THE SPEAKER:
Montana works as a Machine Learning Engineer with a diverse team at Instacart to drive growth, reduce costs, and ensure they can reliably deliver the core product: your groceries, in an hour. He has also been the Chief Scientist at RescueTime and founder of two other startups that used machine learning to differentiate their apps.
ABOUT DATA COUNCIL:
Data Council (https://www.datacouncil.ai/) is a community and conference series that provides data professionals with the learning and networking opportunities they need to grow their careers. Make sure to subscribe to our channel for more videos, including DC_THURS, our series of live online interviews with leading data professionals from top open source projects and startups.
FOLLOW DATA COUNCIL:
Twitter: https://twitter.com/DataCouncilAI
LinkedIn: https://www.linkedin.com/company/datacouncil-ai
Facebook: https://www.facebook.com/datacouncilai
Eventbrite: https://www.eventbrite.com/o/data-council-30357384520
Видео Machine Learning from Development to Production at Instacart | Instacart канала Data Council
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Get Ready for ML! Level Up Your Data Lake with Delta and lakeFS | TreeverseBuilding a scalable experimentation platform at Spotify by Karina BunyikMachine Learning Engineer Interviewing Tips with AlexWalmart Data Science Case Study Mock Interview: Underpricing AlgorithmYu Guo: Scaling experimentation at Airbnb: Platform, Process, and People - CXL LIVE 2018How to deploy machine learning models into productionScaling Machine Learning on Kubernetes and Kubeflow with SageMaker - AWS Online Tech TalksChris Davis, Machine Learning Use Cases for Cybersecurity | KringleCon 2019Why The Gig Economy Is A Scam | James Bloodworth | TEDxManchesterAcing the Product Data Science Interview (for Facebook, Google, and Amazon Interviews)Neo4j Online Meetup #24: Kaggle Instacart Market Basket Analysis with Neo4jThe Rise Of Instacart And Online Grocery DeliveryReal Talk with LinkedIn Staff Machine Learning EngineerMonitoring models in production - Jannes KlaasTrying Instacart For The First Time! | How Much $ Did I Make?!Five Data Science Project IdeasInstacart market basket analysis | Start with Kaggle | PythonData pipeline at Spotify – from the inception to the production - Rafal WojdylaReal Talk with Instagram Data Scientist