KomFi. Academy

medium · FRM Part 2 Current Issues

A bank uses a black-box neural network for credit limit decisions. To provide 'adverse action notices,' it employs a local surrogate model technique. A validator finds that for a single applicant, two different 'post-hoc' explainers provide conflicting reasons for rejection.

This phenomenon highlights which specific risk in XAI validation?

  1. Demographic parity concerns group-level fairness in outcomes across protected classes, not whether an explainer reflects the model's local logic.
  2. The lack of 'local fidelity,' where the surrogate model fails to accurately map the complex model's behavior in the specific region of that applicant's data.
  3. The exclusion fallacy describes a model reconstructing a banned attribute via proxy variables, unrelated to a validation tool's instability across post-hoc explainers.
  4. Overfitting concerns how well the model generalizes to unseen data, whereas conflicting explainers reflect instability in the post-hoc tools, not the model itself.

Sign up free to see the explanation and track your rank →

More FRM Part 2 Current Issues practice

All Current Issues questions · FRM Part 2 study guide · FRM Part 2 glossary · FRM Part 2 flashcards