AI Foundations
Feature
A measurable input or characteristic a model uses to make a prediction.
Example
A house-price model uses square footage and neighborhood as inputs for each prediction.
Why it matters
It gives a prediction useful clues instead of forcing the system to treat every detail equally.
You'll hear it
“Does the prediction use delivery distance, or just the order value?”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Can two clues carry much the same information?
- Yes. Closely related clues can overlap, so adding both may contribute little extra value.
- Can a feature be a word or image?
- Yes. Software can turn words, pictures or sounds into numbers an AI can work with.
- Why does feature selection matter?
- Poorly chosen clues can distract the system or leave out information needed for a fair, accurate result.