A data scientist trains a classification model on a dataset of 10,000 labeled emails to distinguish spam from non-spam. The model achieves 99% accuracy on the training data but only 70% accuracy on a held-out test set. Which term best describes this situation?

A) Underfitting

Underfitting occurs when the model fails to capture patterns in the training data, resulting in poor performance on both training and test sets, which is not the case here.

C) Bias-variance tradeoff

Bias-variance tradeoff is a conceptual framework explaining the tension between underfitting and overfitting. It is not the direct term for the observed performance pattern.

D) Regularization

Regularization is a technique used to reduce overfitting by penalizing complex models. It is a solution, not the problem described.

What does this AI-900 question test?

Read the scenario before looking for a memorised answer.

What is the correct answer to this question?

The correct answer is: B) Overfitting — When a model performs exceptionally well on training data but poorly on unseen data, it has learned the training data too closely, including noise and random fluctuations. This is known as overfitting. Underfitting would show poor performance on both sets. Bias-variance tradeoff is a broader concept, and regularization is a technique to mitigate overfitting. Thus, overfitting is the correct term.

What should I do if I get this AI-900 question wrong?

Then try more questions from the same exam bank and focus on understanding why the wrong options are tempting.