TF-IDF
Definition
TF-IDF weights words according to how often they appear in the individual document and how rare they are in the entire collection.
A weighting that boosts frequent terms in a document and downweights terms frequent in the entire corpus.
Simply explained
A word is particularly distinctive if it occurs often in this document but rarely in the other documents.
Why it matters in practice
The term helps to select, develop, evaluate AI systems in a well-founded manner and realistically assess their technical risks.
Example from business
An internal search prioritizes rare model numbers over common words.
Limits and pitfalls
- Variants of the formula differ; word order and synonyms are not captured and corpus changes shift weights.
Origin & history
Salton and Buckley systematized widespread term weightings for information retrieval in 1988.
Use in mid-sized companies
- Possible application: An internal search prioritizes rare model numbers over common words.
Frequently asked questions
What does TF-IDF mean?
A weighting that boosts frequent terms in a document and downweights terms frequent in the entire corpus. What should be considered? Variants of the formula differ; word order and synonyms are not captured and corpus changes shift weights.
Sources
- Term-weighting approaches · Salton and Buckley, Term-weighting approaches
Source checked on 10.10.2026. Editorial application examples are hypothetical; no evidence of real customer results.
Editorially reviewed on: