A regulator requires that any customer refused credit receive the reasons. A team proposes a deep neural network slightly more accurate than an interpretable model. How should this be assessed?

• AAdopt the interpretable model, because a duty to give reasons makes explainability a requirement rather than a preference.
• BAdopt the neural network, since accuracy is the primary duty to customers.
• CAdopt the neural network and have it generate an explanation of each refusal.
• DAdopt the neural network and publish a model card, which satisfies the requirement.