nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #172

You are an ML engineer at a manufacturing company. You are creating a classification model for a predictive maintenance use case. You need to predict whether a crucial machine will fail in the next th

The correct answer is C. The model with the highest recall where precision is greater than 0.5.. The two requirements translate directly into metric constraints: (1) 'prioritizes detection' = maximize Recall (catch as many actual failures as possible); (2) 'more than 50% of triggered maintenance jobs address an imminent failure' = Precision > 0.5 (of all times the model pred

Submitted by asante_acc· Apr 18, 2026ML model development

Question

You are an ML engineer at a manufacturing company. You are creating a classification model for a predictive maintenance use case. You need to predict whether a crucial machine will fail in the next three days so that the repair crew has enough time to fix the machine before it breaks. Regular maintenance of the machine is relatively inexpensive, but a failure would be very costly. You have trained several binary classifiers to predict whether the machine will fail, where a prediction of 1 means that the ML model predicts a failure. You are now evaluating each model on an evaluation dataset. You want to choose a model that prioritizes detection while ensuring that more than 50% of the maintenance jobs triggered by your model address an imminent machine failure. Which model should you choose?

Options

  • AThe model with the highest area under the receiver operating characteristic curve (AUC ROC)
  • BThe model with the lowest root mean squared error (RMSE) and recall greater than 0.5.
  • CThe model with the highest recall where precision is greater than 0.5.
  • DThe model with the highest precision where recall is greater than 0.5.

How the community answered

(36 responses)
  • A
    8% (3)
  • B
    11% (4)
  • C
    78% (28)
  • D
    3% (1)

Explanation

The two requirements translate directly into metric constraints: (1) 'prioritizes detection' = maximize Recall (catch as many actual failures as possible); (2) 'more than 50% of triggered maintenance jobs address an imminent failure' = Precision > 0.5 (of all times the model predicts failure=1, more than half must be true failures). Therefore, choose the model with the highest Recall where Precision > 0.5. Option D reverses the priority (maximize Precision, Recall > 0.5), which would miss too many actual failures. AUC ROC (A) is a threshold-agnostic aggregate metric and doesn't enforce the specific Precision floor. RMSE (B) is a regression metric, not applicable to binary classification.

Topics

#Model Evaluation#Precision and Recall#Classification Metrics#Predictive Maintenance

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice