📄 ResumeParser – ML-Powered Resume Matching System

ResumeParser is an end-to-end intelligent resume screening tool that helps recruiters rank candidate resumes based on semantic relevance to a job description. It leverages NLP and machine learning to extract, parse, and match resumes—going beyond basic keyword filtering to true contextual understanding.

---

🚀 Features

• ✅ Extracts structured data (skills, education, experience) from .docx resumes
• 🧠 Uses Sentence-BERT for semantic JD–resume matching
• 🔍 Highlights matched keywords from resumes and JD
• 📊 Classifies candidates into shortlist, considered, and unconsidered buckets
• 🌐 Streamlit UI for evaluating match score between a JD and uploaded resume
• 🧩 Modular design to build a pluggable API for Workday or ATS integration

---

🧰 Tech Stack

• Python 3.8+
• spaCy
• sentence-transformers
• Streamlit
• python-docx
• scikit-learn
• fuzzywuzzy

---

⚙️ Setup Instructions

1. Clone the repository

git clone https://github.com/your-username/ResumeParser.git
cd ResumeParser

2. Create and activate virtual environment (recommended)

python -m venv env
# Windows
env\Scripts\activate
# macOS/Linux
source env/bin/activate

3. Install dependencies

pip install -r requirements.txt
python -m nltk.downloader punkt
python -m spacy download en_core_web_sm

4. Run the Streamlit app

streamlit run app.py