AdvancedBusiness trackZA-CP-04

AI Credit Scoring with Fairness Audit

Build a credit model on imbalanced data, then audit it for disparate impact across protected groups and publish a model card.

10 Guided Steps240h Internship TierSubmit: GitHub repo or evidence pack + live demo / report + README + milestone logbookVerified CertificateAI Rubric Graded

Program Overview

Build a credit model on imbalanced data, then audit it for disparate impact across protected groups and publish a model card.

What you submit

GitHub repo or evidence pack + live demo / report + README + milestone logbook

How it is graded

Problem framing15
The business question, decision owner and success measure are stated in two or three sentences.
Data & method25
Sources are named, data is cleaned and explained, and the method fits the question.
Analysis & model25
The model or analysis is correct, assumptions are on their own sheet, and sensitivity is tested.
Recommendation20
A clear recommendation with numbers, risks and the next step, not just a list of findings.
Deck & communication15
A short deck or memo a manager could read in five minutes.

Pass 60% · Merit 75% · Distinction 90%

Learning Outcomes

240-hour South Africa programme. The FSCA and SARB have moved to outcome-based regulation of AI in financial services. Fairness evidence is now expected.

Target Audience

Engineering Students

Diploma, B.Tech, B.E., BCA, MCA, or M.Tech students seeking practical experience.

Aspiring Developers

Developers who want to build proof-of-work capstone projects for tech resumes.

Job Seekers

Graduates looking for AI-evaluated code review & verified industry credentials.