DY0-001 · Question #86
A data scientist receives an update on a business case about a machine that has thousands of error codes. The data scientist creates the following summary statistics profile while reviewing the logs…
The correct answer is A. Sparse matrix. With 19,000 possible error-code features and each machine reporting only a handful (median of 7), your feature matrix will be extremely sparse (most entries zero) which can negatively impact both storage and model performance unless you address it (e.g., via sparse data…
Question
A data scientist receives an update on a business case about a machine that has thousands of error codes. The data scientist creates the following summary statistics profile while reviewing the logs for each machine:
Which of the following is the most likely concern with respect to data design for model ingestion?
Exhibit
Options
- ASparse matrix
- BGranularity misalignment
- CInsufficient features
- DMultivariate outliers
How the community answered
(36 responses)- A78% (28)
- B3% (1)
- C11% (4)
- D8% (3)
Explanation
With 19,000 possible error-code features and each machine reporting only a handful (median of 7), your feature matrix will be extremely sparse (most entries zero) which can negatively impact both storage and model performance unless you address it (e.g., via sparse data structures or dimensionality reduction).
Topics
Community Discussion
No community discussion yet for this question.