Partial Dependence Plot
A visualisation technique that shows the marginal effect of one or two features on a model's predicted output, averaged across the distribution of all other features.
In plain language
A graph showing how changing one aspect of the data affects what the AI predicts. For example, a loan approval model's partial dependence plot might show that as someone's income increases, their approval probability rises steadily.
Why this matters
Partial dependence plots support model interpretability and governance by making relationships between inputs and outputs visible to non-technical stakeholders. They help you verify that the model is learning sensible relationships and can support defensibility in regulated decisions.
Relevance
GovernanceEnhances interpretability and explainability of model decisions, supporting governance requirements around transparency and defensibility.
Related terms
Putting partial dependence plot into practice in your organisation?
Ready to transform your AI strategy?
Partner with Australia's AI strategy and governance specialists. From adoption roadmaps to ISO 42001 audit readiness.