Designing an ML workflow in the cloud
ML is an end-to-end (E2E) iterative process consisting of multiple phases. As we explain the different phases throughout the rest of the book, we will align to the general guidelines provided by Cross Industry Standard Process for Data Mining (CRISP-DM) consortium. The CRISP-DM reference model was conceived in late 1996 by three pioneers of the emerging data mining market and continued to evolve through participation from multiple organizations and service suppliers across various industry segments. The following diagram shows the different phases of the CRISP-DM reference model:
Figure 7.8 – Phases of the CRISP-DM reference model (redrawn from https://www.the-modeling-agency.com/crisp-dm.pdf)
This model is still considered a baseline and a proven tool for conducting successful data mining projects as its application is neutral and applies well to a wide variety of ML pipelines and workloads. Using the preceding...
