Assessfy Pvt. Ltd Advanced 5 milestones 100 marks

AI-Powered Resume Screener with Bias Auditing

Target year: BE Sem 7-8 (Major Project Phase-I/II) AICTE: 6 credits · ~150 hrs Bloom: Create / Evaluate MU CBCS: AI801 / AIDLO8021 BE Project

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

Build an ML system that ranks resumes against a job description. Critical twist: explicitly audit for demographic + caste/region/gender bias using counterfactual fairness tests. Deliverable includes a fairness-impact report + mitigation strategy (debiasing word embeddings, demographic-blind features).

Course Learning Outcomes (CLOs):
CLO1: Build an end-to-end ML system for a real HR use-case.
CLO2: Apply fairness metrics + counterfactual analysis.
CLO3: Iterate on mitigation strategies + measure impact.
CLO4: Document ethical risks + recommended deployment guardrails.
CLO5: Engage with ethics in AI in a defensible manner.

Industry/societal relevance: India's draft Digital Personal Data Protection Act (DPDPA) makes algorithmic-fairness audits a hiring filter for HR-tech; Hiretual, HirePro, Eightfold AI India.

Milestones

1. Dataset + Job-Spec Setup

15 marks 14d

Curate a synthetic-but-realistic Indian resume corpus (with explicit demographic attributes for audit). 3 representative JD templates.

2. Ranking Model Baseline

20 marks 18d

Encode JD + resumes with sentence-transformers. Rank by cosine. Eval NDCG@10.

3. Fairness Audit

25 marks 21d

Run AIF360 audits: demographic parity gap, disparate impact ratio across gender + region + caste-proxy.

4. Mitigation: Debias + Blind

20 marks 21d

Try 3 strategies: debiased embeddings, attribute removal, post-hoc reweighting. Re-audit. Document tradeoffs vs accuracy.

5. Streamlit Dashboard + Audit Report

20 marks 26d

Internal-HR-facing dashboard: ranks + fairness flags + drill-down. 14-page report including ethics + deployment guardrails. Oral defense.

Open internships using this project -->

Skills you'll learn

NLPSentence embeddingsResume parsingRanking models (LambdaRank)Fairness metrics (demographic parityequalized odds)Counterfactual testingAudit reporting

Tools used

Python 3.11sentence-transformersscikit-learnIBM AI Fairness 360 (AIF360)StreamlitGitHubIndian resume samples (synthetic + scraped with consent)

Prerequisites

NLP / Deep Learning; Python advanced; reading research papers; basic ethics-in-AI course

Available mentors

No mentors have signed up for this project yet.

Be the first to mentor

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

AI-Powered Resume Screener with Bias Auditing

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Advanced

AI-Powered Resume Screener with Bias …

Assessfy

Auto-issued on completion One-click LinkedIn add