Case Study

Choosing which error categories to fix first

Case context: A team reviews 150 incorrect predictions from a document classifier. Their error log shows that "Name mismatch" accounts for 6% of the mistakes, while "Low scan quality" and "Unusual formatting" account for most of the rest.

Question: Based on standard error-analysis guidance, what should the team choose to investigate or improve next, and why?

Sample answer: The team should focus on "Low scan quality" or "Unusual formatting" rather than "Name mismatch." Fixing the name-mismatch cases could improve performance by at most 6% of the total errors, so it offers a smaller payoff than the more common categories.

Key points:

  • Prioritize the more frequent categories such as Low scan quality or Unusual formatting.
  • Fixing Name mismatch can remove at most 6% of the errors.
  • Higher-frequency error types usually offer a larger opportunity for improvement.

Rubric: The response must say that the team should prioritize "Low scan quality" or "Unusual formatting" over "Name mismatch," and it must justify that choice by noting that correcting "Name mismatch" can improve results by no more than 6%.

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