AI Resume-Job Matcher

An intelligent resume-job matching application that analyzes the compatibility between resumes and job descriptions using machine learning. Upload your resume and get an AI-powered matching score!

Features

• 📄 Resume Upload: Support for PDF, TXT, and DOCX files
• 💼 Job Description Analysis: Paste job descriptions for instant matching
• 🎯 AI-Powered Matching: Uses advanced NLP and machine learning for accurate matching scores
• 📊 Detailed Analysis: Get text similarity scores and recommendations
• 🎨 Modern UI: Clean, intuitive Streamlit interface

Dataset

This project uses the "AI-Powered Resume Screening Dataset 2025" from Kaggle, which contains:

• 1,000+ resume records with skills, experience, education, and certifications
• Job roles and AI matching scores
• Used to train a regression model that predicts resume-job matching scores

How It Works

1. Text Processing: Extracts and processes text from resumes and job descriptions
2. Similarity Calculation: Uses TF-IDF vectorization and cosine similarity
3. Feature Engineering: Combines text similarity with experience, salary, and project data
4. Machine Learning: Random Forest regression model predicts matching scores (0-100)

Installation

1. Clone the repository:

git clone <repository-url>
cd AI_POWERED_RESUME_SCREENER

2. Install dependencies:

pip install -r requirements.txt

3. Run the application:

streamlit run app.py

Usage

1. Upload Resume: Choose between file upload (PDF/TXT/DOCX) or paste text
2. Enter Details: Provide years of experience, salary expectation, and project count
3. Paste Job Description: Copy and paste the job posting
4. Get Results: Click "Calculate Matching Score" for instant analysis

Matching Score Interpretation

• 80-100: 🌟 Excellent Match - Strong recommendation to apply
• 60-79: 👍 Good Match - Consider tailoring resume further
• 0-59: ⚠️ Low Match - Significant gaps detected

Project Structure

AI_POWERED_RESUME_SCREENER/
├── app.py                    # Main Streamlit application
├── train_models.py          # Model training script
├── requirements.txt         # Python dependencies
├── README.md                # This file
├── data/
│   └── AI_Resume_Screening.csv  # Training dataset
├── src/
│   ├── processing.py        # Data preprocessing and feature engineering
│   └── util.py             # Model utilities and file processing
├── models/                 # Trained model files (generated)
└── assets/                 # Static assets

Model Training

To train the model manually:

python train_models.py

The script will:

• Load and preprocess the dataset
• Calculate text similarities
• Train a Random Forest regression model
• Evaluate performance (R², MAE, RMSE)
• Save the trained model

Technologies Used

• Streamlit: Web application framework
• Scikit-learn: Machine learning and NLP
• Pandas: Data manipulation
• PyPDF2: PDF text extraction
• python-docx: Word document processing
• NumPy: Numerical computing

Model Performance

The regression model achieves good performance in predicting resume-job matching scores based on the training data, with metrics including:

• R² Score: Measure of variance explained
• MAE: Mean Absolute Error
• RMSE: Root Mean Squared Error

File Format Support

• PDF: Portable Document Format (.pdf)
• TXT: Plain text files (.txt)
• DOCX: Microsoft Word documents (.docx)

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

Future Enhancements

• Support for more file formats (DOC, RTF)
• Advanced NLP models (BERT, transformers)
• Skills gap analysis
• Resume improvement suggestions
• Batch processing for multiple resumes

License

This project is for educational purposes. Please check the dataset license on Kaggle for commercial use.

Acknowledgments

• Dataset source: Kaggle AI-Powered Resume Screening Dataset 2025
• Built with ❤️ for better job matching