liveBook · Manning

Qualitative selection

As explained in Delivering Machine Learning Projects: From design to deployment

Qualitative selection is the process of judging candidate models for appropriateness using nonnumeric considerations, context, and requirements.

Qualitative selection judges candidate models as appropriate for use through administrative judgment, context, and project requirements rather than through a single numeric optimum. Quantitative results can narrow the candidate pool, but the final decision should combine evidence, significance, and practical judgment. section 8.3

Make the selection process defensible by:

  • Assembling and recording the information used for selection. section 8.3
  • Assessing the quality and informativeness of testing results before judging their significance. section 8.3
  • Documenting the decision so production behavior can be explained transparently. section 8.3
  • Adjusting testing and selection effort to the project rather than applying every available process. section 8.1

How Delivering Machine Learning Projects: From design to deployment covers it

How deep it goes
Defines judgment and documentation requirements but stops short of prescribing specific qualitative tools or decision criteria.
Examples
Uses candidate models, testing results, quality, informativeness, significance, and production behavior as decision artifacts.
What it assumes
Assumes testing results and candidate models while teaching teams to scale evaluation effort to project needs.
What you can do after
Evaluate/understand model candidates by combining quantitative evidence with documented administrative judgment and explaining deployment decisions.
How it connects
Connects model selection with quantitative aggregation, testing, calibration, documentation, and production behavior.
Cover of Delivering Machine Learning Projects: From design to deployment
liveBookmanning.com
Read Delivering Machine Learning Projects: From design to deployment on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Delivering Machine Learning Projects: From design to deployment. The section links point to the parts of the book it draws on.