What is a common symptom of overfitting?

• A. Low training accuracy and high validation accuracy
• B. Both high training and high validation accuracy
• C. Training accuracy equal to validation accuracy
• D. High training accuracy and low validation accuracy

Answer: (D)

Overfitting occurs when a model models the training data too closely and fails to generalize to new data. A common sign is high accuracy on the training data paired with low accuracy on a separate validation set, showing the model has memorized quirks of the training set rather than learning general patterns. That gap between high training performance and weak validation performance is what this item highlights. If both training and validation accuracy are high, the model is generalizing well; if both are low, it’s underfitting; and if training accuracy is high but validation accuracy is also high, the gap isn’t present, which doesn’t indicate overfitting. Practically, you’d address overfitting by adding regularization, gathering more data, or simplifying the model to help generalization.