📄 Resume Screening System using Machine Learning

📌 Project Overview

The Resume Screening System is an NLP-based Machine Learning project that automates the resume screening process by analyzing resumes, extracting technical skills, comparing them with a job description, calculating similarity scores using TF-IDF and Cosine Similarity, identifying missing skills, and ranking candidates based on job relevance.

This project was developed as part of Machine Learning Task 3 during my internship at Future Interns.

---

🎯 Objectives

• Automate resume screening
• Extract technical skills using NLP
• Compare resumes with job descriptions
• Rank candidates based on similarity
• Identify missing skills
• Visualize candidate rankings

---

🚀 Features

• ✅ Resume text preprocessing
• ✅ NLP-based skill extraction
• ✅ TF-IDF Vectorization
• ✅ Cosine Similarity Matching
• ✅ Candidate Ranking
• ✅ Skill Gap Analysis
• ✅ Data Visualization

---

🛠️ Tech Stack

• Python
• Pandas
• NumPy
• NLTK
• Scikit-learn
• Matplotlib
• Regular Expressions (re)

---

📂 Dataset

The dataset contains 2484 resumes from multiple domains, including:

• Information Technology
• HR
• Engineering
• Finance
• Banking
• Healthcare
• Sales
• Teacher
• Business Development
• And more...

Each record contains:

• Resume Text
• Resume HTML
• Resume Category

---

⚙️ Project Workflow

Resume Dataset
        │
        ▼
Data Preprocessing
        │
        ▼
Skill Extraction
        │
        ▼
Job Description Processing
        │
        ▼
TF-IDF Vectorization
        │
        ▼
Cosine Similarity
        │
        ▼
Resume Ranking
        │
        ▼
Skill Gap Analysis
        │
        ▼
Visualization

---

📸 Project Screenshots

1️⃣ Candidate Ranking

The system ranks resumes based on similarity with the job description.

---

2️⃣ Skill Extraction

Technical skills extracted automatically from resumes using NLP.

---

3️⃣ Match Score Visualization

Visualization of similarity scores for the top-ranked candidates.

---

📊 Sample Output

Category	Match Score	Skills Extracted
Information Technology	92.4%	Python, SQL, Git
Data Science	88.7%	Python, Pandas, ML
HR	63.2%	Communication, Excel

---

📁 Project Structure

FUTURE_ML_03
│
├── dataset/
│   ├── data/
│   └── Resume/
│       └── Resume.csv
│
├── notebook/
│   └── Resume_Screening.ipynb
│
├── screenshots/
│   ├── candidate_ranking.png
│   ├── skill_extraction.png
│   └── match_scores.png
│
├── requirements.txt
├── README.md
└── .gitignore

---

▶️ Installation

Clone the repository

git clone https://github.com/prav-tech/FUTURE_ML_03.git

Go to the project folder

cd FUTURE_ML_03

Install dependencies

pip install -r requirements.txt

Run Jupyter Notebook

jupyter notebook

Open

Resume_Screening.ipynb

---

📌 Future Improvements

• Streamlit Web Application
• Resume PDF Upload
• ATS Score Prediction
• Semantic Matching using BERT
• Resume Parser with spaCy
• Multi-Job Description Support

---

📚 Learning Outcomes

This project helped me gain hands-on experience in:

• Natural Language Processing (NLP)
• Resume Text Preprocessing
• TF-IDF Vectorization
• Cosine Similarity
• Feature Extraction
• Candidate Ranking
• Skill Gap Analysis
• Data Visualization

---

👩‍💻 Author

Pravallika B

B.Tech Computer Science & Engineering

Machine Learning Intern @ Future Interns

GitHub: https://github.com/prav-tech

---

⭐ Acknowledgement

This project was completed as part of the Machine Learning Internship Program at Future Interns.