AI engineering glossary · AI ethics law product
What is global explanation?
Global explanation: A description of how a model behaves across the whole dataset, such as which features matter most on average or how predictions change as one feature varies. It helps teams check whether the model has learned sensible patterns overall.
Global explanation: an example
A global importance chart shows that income and repayment history dominate a credit model, while pin code has a small but non-zero effect.
Related terms
More AI ethics law product terms
- High-risk AI system
- Historical bias
- Homomorphic encryption
- Human oversight
- Implicit feedback
- Individual fairness
- Interpretability
- k-anonymity
Where you learn it
Global explanation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.