Skip to content

What is Underfitting?

Underfitting happens when a machine learning model is too simple to capture the patterns in the training data, leading to poor performance on both training and unseen data.

It occurs when the chosen model lacks sufficient complexity or capacity, such as using a linear model for nonlinear relationships, resulting in high bias and an inability to learn meaningful features from the data.

Key signs include high error rates during training and testing, as the model fails to approximate the true underlying function despite seeing the examples.

It is often addressed by increasing model complexity, adding more features, or reducing regularization to allow better fitting of the data patterns.

Example

Imagine using a straight line to predict house prices based on size when the real relationship is curved; the simple line misses key trends and makes inaccurate predictions for both known and new houses.

Why it matters

Underfitting produces unreliable AI systems that cannot generalize or deliver value, so recognizing and fixing it is essential for building effective models in applications like prediction and classification.

Frequently asked questions

Check if training error is high and similar to test error; this shows the model isn't learning the data patterns well.