# Spam Filter

> A tool that uses AI to keep junk email out of your inbox.

**Field:** Artificial Intelligence  
**Category:** Use Case  
**Also known as:** Email Spam Filter, Junk Mail Filter

## Think of it like

It is like a guard at the door who keeps the junk mail out.

## Definition

A spam filter decides if an email is junk before you see it. It looks at the words, the links, the sender and how the mail was sent. Machine learning gives each message a score for how likely it is to be spam. High scores go to the spam folder, and the rest reach your inbox. When you mark a mail as spam, the filter learns from it.

## Example

A mail that says 'You won a prize, click here' comes from a new address. The filter scores it as likely spam and drops it in the spam folder.

## Why it matters

Without it, junk and scams would bury the mail you want.

## Common mistake

Never checking the spam folder. Real mail gets caught now and then, so look there when a mail is missing.

## Three principles

- **Scores each mail.** How likely it is junk.
- **Learns.** From the mail you mark.
- **Can miss.** Check the spam folder.

## Related terms

- [Classification (Machine Learning)](https://learn.benibix.com/term/ai/classification)
- [Machine Learning](https://learn.benibix.com/term/ai/machine-learning)
- [Fraud Detection](https://learn.benibix.com/term/ai/fraud-detection)
- [CAN-SPAM Act](https://learn.benibix.com/term/marketing/can-spam-act)
- [Naive Bayes](https://learn.benibix.com/term/ai/naive-bayes)
- [Spam (Email)](https://learn.benibix.com/term/general/spam)

## Taught in

- [Spam and Fraud Detection](https://learn.benibix.com/learn/ai-use-case/spam-and-fraud-detection): AI Assistants and Chatbots, 11/13

![Three rows, each reading what comes in, the guess, and what happens. A new email goes to the spam filter, which asks how likely it is junk, and sends it to the inbox or the spam folder. A card payment goes to fraud detection, which asks if it fits this person, and lets it pass or holds it and asks. The words see you go to predictive text, which asks what word comes next, and offers soon, later and tomorrow.](https://learn.benibix.com/diagrams/ai2-everyday-ai.svg)

---

Source: https://learn.benibix.com/term/ai/spam-filter
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
