An organization is using machine learning to make predictions. One of their datasets mistakenly includes mislabeled data. How will the prediction be impacted?

Question

Options

• AIncreased risk of privacy leaks
• BIncreased risk of inaccuracy
• CDecreased model compatibility
• DDecreased model training time

• A
  3% (1)
• B
  94% (32)
• C
  3% (1)

Explanation

Machine learning models learn patterns from training data. If that data contains mislabeled examples, the model learns incorrect associations and produces inaccurate predictions - this is the classic 'garbage in, garbage out' principle. Option A (privacy leaks) is unrelated to data labeling errors. Option C (model compatibility) is a deployment/framework concern, not a data quality concern. Option D is incorrect because mislabeled data does not speed up training; if anything, a model may require more iterations to converge on the noisy signal.

No community discussion yet for this question.