Enterprise ML -- Why building and training a "real-world" model is hard

What does it take to deliver a machine learning (ML) application that provides real business value to your company? Once you've done that and proved the substantial benefit that ML can bring to the company, how do you expand that effort to additional use cases, and really start to fulfill the promise of ML? And then, how do you scale up ML across the organization and streamline the ML development and delivery process to standardize ML initiatives, share and reuse work and iterate quickly? What are the best practices that some of the world's leading tech companies have adopted? Over a series of articles, my goal is to explore these fascinating questions and understand the challenges and learnings along the way.