# What is Underfitting? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Model Limitations  
> **Canonical Citation:** [https://spidits.com/ai-glossary/underfitting](https://spidits.com/ai-glossary/underfitting)

## Definition
Underfitting is a training error that occurs when a machine learning model is too simple to capture the underlying structure and patterns in the training dataset, resulting in poor performance on both training and validation data.

## Architectural Mechanics & Deep Dive
Underfitting is a training failure mode where a machine learning model is too simple to capture the underlying structure of the training data. An underfitted model exhibits poor accuracy on both the training set and validation set, requiring a more complex model architecture, better features, or longer training.

## Industry Applications & Real-World Use Cases
Model architecture design, feature engineering validation, and training monitoring.

## Frequently Asked Questions

### What is the difference between overfitting and underfitting?
Overfitting is when a model is too complex and memorizes training noise (performing well on training data but poorly on test data). Underfitting is when the model is too simple and fails to learn the basic patterns (performing poorly on both datasets).

### How do developers resolve underfitting?
By increasing model complexity (e.g., adding layers or parameters), training for more epochs, engineering more predictive features, or reducing regularization constraints.

## Related Terminology
- [overfitting](https://spidits.com/ai-glossary/overfitting)
- [bias-variance-tradeoff](https://spidits.com/ai-glossary/bias-variance-tradeoff)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*