Question 32
UnclassifiedWhat does a high variance, low bias model typically exhibit?
Correct answer: B
Explanation
A model with high variance changes a lot with different training data, so it fits noise and idiosyncrasies in the sample. That behavior is called "overfitting," because the model learns the training set too closely and performs worse on new data.
Why each option is right or wrong
A. Underfitting
B. Overfitting
A model with high variance is highly sensitive to the particular training sample, so its predictions change materially if the data are resampled; that instability is the hallmark of fitting noise rather than the underlying signal. In bias-variance terms, low bias means the model is flexible enough to capture the training data closely, and when that flexibility is excessive it typically degrades out-of-sample performance, which is the definition of overfitting.
C. Both underfitting and overfitting
D. Perfect generalization