The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Automated Machine Learning with Erez Barak - #323
Dec 6, 2019
Erez Barak, Partner Group Manager of Azure ML at Microsoft, shares his expertise in automated machine learning. He discusses the transformative impact of AutoML on the data science process, emphasizing its role in featurization, model selection, and hyperparameter tuning. The conversation also explores the balance between automation and human intuition, alongside the importance of systematic model building in lead scoring and ensuring model fairness. Erez dives into practical post-deployment use cases and the evolving landscape of MLOps.
AI Snips
Chapters
Transcript
Episode notes
Erez's background in marketing automation
- Erez worked at Optify in marketing automation, leveraging data as a unique asset.
- They focused on lead scoring and likelihood-to-buy predictions before machine learning was prevalent.
Defining AutoML
- There's no single definition of AutoML, but it uses machine learning to improve the machine learning creation process.
- This results in more efficient, accurate, and structured model development.
AutoML's role in the machine learning process
- AutoML automates the end-to-end machine learning process.
- Featurization is crucial, as model accuracy depends heavily on how effectively the data is featurized.