Explore real-world case studies and best practices for successfully implementing AI and machine learning systems in production environments. Learn about concept drift, common pitfalls in A/B testing, offline versus online measurements, and systems that learn in production. Gain valuable insights from a decade of experience building and operating AI systems at Fortune 500 companies across various industries. Understand how to identify and correct model decay, avoid primacy and novelty effects in testing, and set up teams and products for success. Ideal for executives, technical leaders, and product managers seeking to learn from others' mistakes and ensure the effective deployment of AI technologies in their organizations.
What to Expect When You Are Putting AI in Production - Dr. David Talby
Overview
Syllabus
Intro
GARBABE IN GARBAGE OUT
CONCEPT DRIFT: AN EXAMPLE
REUSING MODELS IS A REPUTATION HAZARD
DON'T ASSUME YOU'RE READY FOR YOUR NEXT CUSTOMER
THE PITFALLS OF A/B TESTING
FIVE PUZZLING OUTCOMES EXPLAINED
MODEL DEVELOPMENT SOFTWARE DEVELOPMENT
Taught by
Open Data Science
