Summary
As I stated from the outset, the primary goal of this chapter was to emphasize the many challenges an ML practitioner may face when building an ML solution for a business use case. In this chapter, I introduced you to an example ML use case – the Abalone Calculator – and I used it to show you just how hard the ML process is in reality.
By walking through each step of the process, I explained the complexities involved therein, as well as the challenges you could potentially encounter. I also highlighted why the ML process is complicated, manual, iterative, and continuous, which set the stage for an automated process that is repeatable, streamlined, and reliable using AutoML.
In the next chapter, we will explore how to start implementing an AutoML methodology by introducing you to a native AWS service called SageMaker Autopilot.
