Counterfactual Fairness in Mortgage Lending via Matching and Randomization
This addresses racial inequality in mortgage lending for affected populations, but is incremental as it builds on existing counterfactual fairness methods.
The paper tackles unfairness in mortgage lending by applying counterfactual fairness with a new causal graph on HMDA data, using a matching-based approach to isolate race, and finds that balanced data does not ensure fairness in models.
Unfairness in mortgage lending has created generational inequality among racial and ethnic groups in the US. Many studies address this problem, but most existing work focuses on correlation-based techniques. In our work, we use the framework of counterfactual fairness to train fair machine learning models. We propose a new causal graph for the variables available in the Home Mortgage Disclosure Act (HMDA) data. We use a matching-based approach instead of the latent variable modeling approach, because the former approach does not rely on any modeling assumptions. Furthermore, matching provides us with counterfactual pairs in which the race variable is isolated. We first demonstrate the unfairness in mortgage approval and interest rates between African-American and non-Hispanic White sub-populations. Then, we show that having balanced data using matching does not guarantee perfect counterfactual fairness of the machine learning models.