Short Answer

How Evaluation Data Changes Model Selection

Question: How do a development set and a clear evaluation metric affect the way a machine learning team decides which model ideas deserve more work?

Sample answer: They let the team compare ideas quickly and see whether a change produces a meaningful gain or not. With that feedback, the team can keep improving promising models and drop weak ones without spending a long time manually testing each option.

Key points:

  • Helps the team compare ideas quickly.
  • Shows whether a change is worthwhile.
  • Lets the team continue with strong ideas and discard weak ones.

Rubric: The answer should explain that a development set and metric make it easy to compare model ideas quickly, judge whether each change improves performance, and decide which ideas to keep refining versus which to stop pursuing.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI