Model interpretability describes how well people can understand how an AI model arrives at its results. Simple models such as decision trees are inherently easy to read; for complex neural networks, techniques that reveal the influence of individual features can help. Interpretability matters for debugging, trust and regulatory requirements, for example when a loan rejection has to be justified.
Explainability (explainable AI, XAI) describes how well one can understand why an AI system reached a particular result. It covers methods that show which inputs influenced a decision most, as well as practical aids such as source references and logs. Explainability matters for trust, troubleshooting and regulation – for example when a bank has to justify why an application was declined.
AI transparency means disclosing when AI is involved, which data and sources its results are based on, and how decisions are reached. This includes labelling AI content, traceable source references, logs and documented changes. Transparency builds trust, makes troubleshooting easier and is partly required by law, for example by the EU AI Act's transparency obligations, under which people should be able to tell that they are interacting with an AI.
Algorithmic transparency means it is possible to understand how an automated system reaches a result: which data it uses, which rules it follows and where its limits lie. This builds trust, makes errors easier to trace and is increasingly a legal requirement, for example through information duties under the GDPR and the EU AI Act. In practice, documentation, source citations, logs and clear notices for affected people help.
A decision tree is a model that represents a decision as a sequence of simple yes/no questions: each branch tests one feature and each leaf gives an outcome. In machine learning, such trees are learnt automatically from data and used for classification or forecasting. Their main strength is transparency – for instance, showing why a loan application was flagged based on income, term and payment history.
