Explain what overfitting is and how to prevent it.

Overfitting occurs when a model learns training data too well, including noise, resulting in poor generalization to new data.\n\n• Signs: High training accuracy, low validation accuracy\n• Prevention techniques: Cross-validation, regularization (L1/L2), dropout, early stopping\n• Data approaches: More training data, data augmentation, feature selection\n\nExample: A decision tree with unlimited depth memorizes training examples. Use pruning, validation sets, and ensemble methods to maintain generalization capability.