Skip to content
LATHICAI Glossary

RAG & Search

Content-based filtering

Making suggestions by matching an item's features to someone's recorded interests.

Example

A reading app suggests books with subjects similar to ones a reader liked.

Why people use it

It suggests items with characteristics similar to things a person already likes.

What you'll hear

“Show me more books on subjects I enjoy.”

What this means for you

Check whether recommendations are narrowing the variety of options you see.

Can you control it?

Sometimes

Sometimes. Your choices depend on the tool and your access. The settings available to an everyday user may differ from those available to the people running it.

Common questions

Is this the same as copying other users' tastes?
No. That is the central idea of collaborative filtering.
Can it recommend a newly added item?
Yes, if the service knows enough about its characteristics to compare it with a person's interests.
Why can the suggestions become repetitive?
Closely matching past preferences may leave little room for unfamiliar subjects or styles.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice