Responsible ML: Interpretability, Fairness & Privacy
Explaining, auditing and protecting models — the obligations that come with shipping them
Explain, audit and protect a model before it decides things about people: why regulation (EU AI Act risk tiers, GDPR, fair-lending adverse action) and plain debugging value make this part of the job, the interpretability taxonomy (intrinsic versus post-hoc, global versus local), global methods with their traps (impurity importance ranked a pure-noise feature at 0.103 above a real predictor at 0.053 while permutation importance gave the noise feature -0.001; correlated twins split permutation importance; PDP range 0.12 hiding ICE curves that swing 0.83), local methods (LIME instability across seeds and kernel widths, Shapley axioms, exact brute-force Shapley values matching TreeSHAP to 3e-9 and summing exactly to the prediction, interaction values, counterfactual recourse, Integrated Gradients, Grad-CAM, why attention and LLM self-explanations are not explanations), and turning SHAP into adverse-action reason codes without reading it as causal; fairness (protected attributes and proxies, demographic parity, equal opportunity and equalized odds, predictive parity, calibration within groups, the impossibility theorem demonstrated with numbers, individual versus group fairness, sources of bias, feedback loops), interventions (reweighing, constraints, group thresholds, the four-fifths rule, audits) with a measured trade-off table; privacy (data minimization, k-anonymity limits, differential privacy with the Laplace and Gaussian mechanisms, composition, DP-SGD, federated averaging, memorization in LLMs, synthetic-data caveats, retention); and governance artifacts (model cards, datasheets, risk assessments, human oversight, incident response). The worked example is a simulated credit model with two groups, run in scikit-learn and SHAP, with every number reproduced from code.
Practice questions (6)
-
View →
Explain TreeSHAP additivity to a risk committee and answer the "so we should raise income?" question
Advanced · Free -
View →
Choose a fairness metric for a hiring screen and for a medical triage model
Advanced · Free -
View →
Design a bias audit for a deployed loan-approval model
Advanced -
View →
Explain epsilon in differential privacy to a product manager and budget a dashboard
Advanced -
View →
Design counterfactual recourse for declined loan applicants and name its constraints
Advanced