Question 33
UnclassifiedMatthews Correlation Coefficient (MCC) is valued because it:
Correct answer: B
Explanation
Matthews Correlation Coefficient uses all four confusion matrix entries—true positives, true negatives, false positives, and false negatives—so it measures performance more completely than accuracy alone. It is valued because this makes it a "balanced metric" and "robust under class imbalance," where one class is much more common than the other.
Why each option is right or wrong
A. Always equals accuracy
B. Provides a balanced metric using all four confusion matrix entries, robust under class imbalance
The Matthews Correlation Coefficient is defined from all four cells of the confusion matrix: TP, TN, FP, and FN, via \((TP\times TN - FP\times FN)/\sqrt{(TP+FP)(TP+FN)(TN+FP)(TN+FN)}\). Because the denominator incorporates every marginal total, the score remains informative even when one class is rare, unlike accuracy, which can be inflated by the majority class.
C. Is faster to compute than F1
D. Is required by NIST AI RMF