Glossary
Updated
Involves choosing inherently interpretable algorithms (decision trees, rule lists) or building hybrid models that balance accuracy and transparency. Governance best practices include documenting model logic, user-testing explanation clarity, and restricting opaque models to low-risk applications when explainable alternatives exist.
Example
A mortgage lender uses an explainable decision-tree model for initial loan approvals. Each decision path is translated into plain-language rules (e.g., “If income > $50K and credit score > 700, approve”), enabling loan officers and auditors to trace every approval directly to human-readable criteria.