One-Hot Encoding
Definition
One-hot encoding marks a category by exactly one set position.
The representation of a categorical attribute as a vector in which exactly one position is one and the others are zero.
Simply explained
For red, green, and blue there are three boxes; only the matching one gets a one.
Why it matters in practice
Helps realistically assess model quality, limits, and technical decisions.
Example from business
The categories red, green, and blue are mapped onto three binary columns.
Limits and pitfalls
- Turning high cardinality into very wide features, not handling unknown categories, or creating unnecessary redundancy in linear models.
Origin & history
Indicator variables are a fundamental encoding method in statistics and machine learning.
Use in mid-sized companies
- Possible example: The categories red, green, and blue are mapped onto three binary columns.
Frequently asked questions
What does one-hot encoding mean?
The representation of a categorical attribute as a vector in which exactly one position is one and the others are zero.
Which mistakes should be avoided?
Turning high cardinality into very wide features, not handling unknown categories, or creating unnecessary redundancy in linear models.
Sources
Source checked on 10.10.2026. Editorial application examples are hypothetical; no evidence of real customer results.
Editorially reviewed on: