Automated Machine Learning: building a conveyor
Talk video
Talk presentation
Data Science
What is the most difficult part of the machine learning process? Data collection? Feature Engineering? Model selection and tuning? Deploy and monitoring? What if you have a whole bunch of models, and business requires you to continuously improve, experiment, re-train and integrate models? And what if you are not even a Data Scientist?
In this talk:
- How to not be drown in chaos, and build structured ML-integration process in a large company
- Taking a close look at what can be automated (spoiler: everything)
- Discussing "conveyor" taking ideas as input can make a great impact on business metrics, through fast and convenient machine learning integration
- What can we achieve by using very basic and simple models
Mikhail Ovchinnikov
Facebook
- Engineering Manager at Facebook
- Primary areas of interest are: security projects and Anti-spam, high availability distributed systems, large-scale machine learning, infrastructure management and DevOps
- Hands-on experience not only in backend engineering but also in cloud solutions, mobile development, and frontend engineering