Analysis
Auditing Bias in a Fintech Credit Scoring Model
Overview
What this challenge is about.
Conduct a quantitative fairness audit using a public proxy dataset (e.g., the UCI Adult or Give Me Some Credit dataset re-framed as BNPL decisions) and apply at least three fairness metrics (demographic parity, equal opportunity, calibration). Map findings to the EU AI Act's high-risk system requirements and the FCA's Consumer Duty. Constraints: you may not retrain the model — your remit is audit and governance, not engineering. Success looks like a clear identification of which subgroups face harm, a defensible recommendation on whether to deploy/pause/remediate, and a governance playbook the CRO could adopt next quarter.
The Brief
What you'll do, and what you'll demonstrate.
Does Zilch's credit scoring model produce ethically and legally defensible outcomes across protected groups, and what governance controls should follow?
Earning criteria — what you'll demonstrate
- Apply quantitative fairness metrics to evaluate AI systems for disparate impact
- Translate ethical concerns into regulatory and governance requirements
- Critically assess trade-offs between competing fairness definitions
- Communicate AI risk findings to non-technical executive audiences
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.