MLA-C01 ML Model Development Practice Question

A team wants to evaluate a binary classification model for credit risk. They need to understand the trade-off between false positives and false negatives. Which TWO metrics should they use? (Select TWO.)

⚠ Common exam trap

The trap here is selecting AUC-ROC as a metric for understanding the trade-off between false positives and false negatives, when AUC-ROC provides a threshold-independent summary rather than the direct trade-off that precision and recall offer.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Recall

Recall (A) is correct because it measures the proportion of actual positives (e.g., true defaults) that the model correctly identifies, directly quantifying the cost of false negatives, which is critical in credit risk where missing a defaulter is costly. Precision (B) is correct because it measures the proportion of predicted positives that are actually positive, directly quantifying the cost of false positives, such as rejecting good customers; together, recall and precision expose the false-positive/false-negative trade-off. NDCG (C) is a ranking-quality metric for graded relevance in search/recommendation, not binary classification. AUC-ROC (D) summarizes ranking performance across thresholds but does not separately expose the precision/recall trade-off the team wants to evaluate. RMSE (E) is a regression error metric and is inappropriate for binary classification.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Recall
Why this is correct
Recall measures the proportion of actual positives correctly identified, directly exposing false negatives — missed credit risks. Pairing it with precision, which exposes false positives, quantifies the trade-off the team needs. Recall alone satisfies the false-negative half of the stem's requirement, making it one of the two correct metrics.
✓
Precision
Why this is correct
Precision measures the proportion of predicted positives that are truly positive, directly quantifying false positives. For credit risk, this reveals how many approved applicants would actually default, satisfying the stem's need to understand the false-positive side of the trade-off. Recall covers the false-negative side.
✗
NDCG
Why it's wrong here
NDCG measures ranking quality in search or recommendation output, using graded relevance positions, so it cannot express the false-positive versus false-negative trade-off in binary credit-risk classification. It is tempting because it evaluates model output, but it would be the right choice for ranking tasks, not threshold-based binary decisions.
✗
AUC-ROC
Why it's wrong here
AUC-ROC summarises performance across all thresholds as a single aggregate number, so it does not expose the specific false-positive versus false-negative trade-off at a chosen operating point. It is tempting because it is a standard binary classification metric, but it would be correct when comparing overall discriminative ability rather than selecting a threshold.
✗
RMSE
Why it's wrong here
RMSE measures the average magnitude of error for continuous numeric predictions, so it cannot represent false positives or false negatives in binary credit-risk classification. It is tempting because it is a common evaluation metric, but it would be the correct choice for regression tasks predicting continuous values, not classification.

Go deeper

MLA-C01 ML Model Development Practice Question

Why each option matters

Option-by-option breakdown

Related to this question