Model Architecture and Interpretability

From The Foundation for Best Practices in Machine Learning
Technical Best Practices > Fairness & Non-Discrimination > Model Architecture and Interpretability

Model Architecture and Interpretability


Choose Model architecture that maximizes interpretability and identification of causes of unfairness. Consider different methodologies within the same Model architecture (ex. monotonic XGBoost, explainable neural networks). Evaluate whether Product Aims can be accomplished with a more interpretable Model.


To (a) provide information that can guide Model-builders; (b) ensure that Model decisions are made in line with expectations; (c) allow Product Subjects and/or End Users to understand why they received corresponding Outcomes; (d) help inform the causes of Fairness issues if issues are detected; and (e) highlight associated risks that might occur in the Product Lifecycle.

Additional Information