nerdexam
IBM

C1000-012 · Question #28

A developer is using machine learning techniques to train a system which will identify fraudulent insurance claims. Which would be best suited for training data?

The correct answer is A. Samples of known fraudulent and legitimate claims. See the full explanation below for the reasoning.

Question

A developer is using machine learning techniques to train a system which will identify fraudulent insurance claims. Which would be best suited for training data?

Options

  • ASamples of known fraudulent and legitimate claims
  • BA set of known legitimate claims mixed in with random claim samples
  • CA set of known fraudulent claims mixed in with random claim samples
  • DA new set of unknown claims

How the community answered

(23 responses)
  • A
    70% (16)
  • B
    17% (4)
  • C
    9% (2)
  • D
    4% (1)

Community Discussion

No community discussion yet for this question.

Full C1000-012 Practice