This scenario is a clear violation of the fairness principle. Fairness in Microsoft’s Responsible AI framework is about ensuring AI systems do not create unjustified bias or discriminatory outcomes—especially when decisions affect people’s access to opportunities such as credit, employment, housing, or education. A rule or learned behavior that rejects all applicants over a certain age creates a systematic, categorical disadvantage for a protected demographic group and indicates a discriminatory decision boundary rather than an individualized assessment of creditworthiness.

Even if the model designers believed age correlates with risk, using a hard cutoff that rejects every applicant older than 60 is not an equitable approach. It suggests the model is either using age directly as a dominant feature or reflects biased training data/labels that encoded discriminatory outcomes. Fairness requires you to evaluate model outcomes across groups (for example, age brackets), measure disparate impact, and apply mitigations such as feature review (removing or constraining sensitive attributes), rebalancing training data, adjusting thresholds, or using fairness-aware training/evaluation methods. It also requires governance and review of high-stakes automated decisions.

The other principles are not the best match: transparency concerns explainability and user understanding, accountability concerns human oversight and ownership, and reliability and safety concerns consistent and safe operation. The core issue here is discriminatory treatment across an age group— fairness .