Projects / Computer Science / Computer Science project 4

Resume Screening and Ranking System

Approx. component budget: Rs. 0 - 1,000

Objective

Compare keyword matching with semantic matching and show how the ranking changes, while checking the system for unfair bias.

What you will build

A tool that reads resumes (PDF or text), extracts skills, education and experience, and ranks them against a job description with a score and a short reason for each rank.

Results you can expect

• Ranking agreement with a human-made ranking (for example Spearman correlation) on 30 resumes
• Skill extraction accuracy
• And a bias check on name and gender changes

What you will learn

Text extraction, named entity recognition, sentence embeddings, similarity scores, and fairness in hiring tools.

Tools and notes

Python, spaCy, sentence-transformers, pdfplumber, Streamlit. Use made-up or consented resumes only, and keep a human in the final decision.

Resume points from this project

• Built and tested Resume Screening and Ranking System; objective: compare keyword matching with semantic matching and show how the ranking changes, while checking the system for unfair bias.
• Measured and analysed ranking agreement with a human-made ranking (for example Spearman correlation) on 30 resumes and skill extraction accuracy; wrote the report and presented the results in a viva. Add your own numbers: [x].

Replace [x] with your own measured results. Write only what you really did.

More computer science projects

Back to all projects