# What is Feature? Definition & Technical Mechanics

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

## Definition
A Feature is an individual, measurable property or input variable used by a machine learning model to make predictions. In tabular datasets, features correspond to columns (e.g. square footage, age of home).

## Architectural Mechanics & Deep Dive
A feature is an individual, measurable property or characteristic of a data point used as an input to a machine learning model. In tabular data, features correspond to columns (e.g., age, income, location). In computer vision and NLP, raw inputs are converted into abstract numerical features by convolutional or transformer layers to perform classification or regression.

## Industry Applications & Real-World Use Cases
Tabular machine learning datasets, model regression features, and neural inputs

## Frequently Asked Questions

### What is feature engineering?
The manual process of combining, cleaning, and transforming raw variables to create more predictive features for machine learning models.

### How does deep learning bypass feature engineering?
Deep learning neural networks extract and select hierarchical features automatically through hidden layer activation runs.

## Related Terminology
- [label](https://spidits.com/ai-glossary/label)
- [machine-learning](https://spidits.com/ai-glossary/machine-learning)
- [one-hot-encoding](https://spidits.com/ai-glossary/one-hot-encoding)

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