IntelliCV is a machine learning–powered web application that automatically analyzes your resume or CV. Built using Streamlit, it takes input resumes (PDF or DOCX), cleans the text, extracts features using TF-IDF, and classifies them using a pre-trained Support Vector Classifier (SVC).
- 📄 Supports PDF and DOCX resume uploads
- 🧹 Preprocesses resumes with custom text cleaning
- 🔍 Uses TF-IDF Vectorization for text feature extraction
- 🧠 Predicts job category using trained SVC model
- 🌐 Simple, interactive Streamlit UI
- 🧰 Easily extendable for more categories or resume analysis features
- Python
- Streamlit
- scikit-learn
- PyPDF2
- python-docx
- pickle (for model + encoder serialization)
📁 intellicv/
│
├── app.py # Streamlit app script
├── requirements.txt # Dependencies for running the app
├── README.md
|── .gitattributes
|── .gitignore
│
├── data/ # Raw resumes and training dataset
│ ├── resume_dataset.csv
│
├── notebooks/ # Jupyter notebooks for analysis
└── Resume_Screening.ipynb
-
Clone the repository
git clone https://github.com/yourusername/intellicv.git cd intellicv -
Create a conda or virtual environment (optional but recommended)
conda create -n intellicv-env python=3.13 conda activate intellicv-env
-
Install the required packages
pip install -r requirements.txt
-
Run the Streamlit app
streamlit run app.py
The model was trained using a labeled dataset of resumes across various job roles. TF-IDF was used for feature extraction, and Support Vector Machine (SVC) was used for classification.
- Add detailed resume analysis (skills, experience, etc.)
- Visualize prediction confidence and key terms
- Allow batch resume uploads and classification
- Integrate with job recommendation APIs
Suchismita Bose
Made with 💚 & 🐍