Underfitting
Domain: Evaluation
🎯 Motivation
The model is too simple to capture the patterns in the data. Performs poorly on both training and test data.
📋 Concrete Example
Underfit model: 60% on training data, 55% on test data. It has not learned enough. Fix: more complex model, more training, better features.
🔗 Analogy
A student who did not study enough - they score 55% on both practice and real exams. They have not learned the material. Underfitting is not learning enough.