# Machine Learning (ML)

> Machine learning (ML) is software that learns patterns from examples rather than being explicitly programmed with rules — so it can make predictions or decisions on data it hasn't seen before.

_Source: https://plenaura.com/glossary/machine-learning · Last updated: 2026-06-03 · Plenaura_

## Key points

- Instead of coding every rule by hand, you show the system examples and it learns the pattern — ideal when the rules are too complex to write out.
- Powers everyday business use cases: forecasting demand, scoring risk, detecting fraud, recommending products.
- A model is only as good as its data; quality, relevance, and freshness of examples drive the results.
- It's the broad field; deep learning and large language models are specific, more advanced branches of it.

## FAQ

### What's the difference between machine learning and AI?

AI is the broad goal of making software behave intelligently. Machine learning is the most common way to get there today — learning patterns from data rather than following hand-written rules. Most systems people call "AI" are built on machine learning.

### How much data do we need to use machine learning?

It depends on the problem. Some tasks work with a few hundred good examples; others need far more. Just as important as volume is quality and relevance — clean, representative data beats a large but messy dataset.