Explain 'Underfitting'.

Explain 'Underfitting'.

Approach: Describe a model that is too simple to capture the underlying data trend.

Occurs when a model is too simple to learn the relationship between features and labels. This results in high error on both training and testing sets. It usually happens when using a linear model for non-linear data.

Follow-up: How do you fix underfitting?

Key concepts: high bias, training error, complexity.