You are a machine learning engineer working for a bank, and you have developed a custom model to predict whether a loan application should be flagged for human review. The input features for this model are stored in a BigQuery table. The model has demonstrated strong performance in testing, and you are preparing to deploy it into production. However, due to stringent compliance requirements, the model must provide explanations for each of its predictions to ensure transparency and accountability. Your goal is to integrate this functionality into your model code with minimal effort while ensuring the explanations are as accurate as possible. What should you do?