🧠 HR Employee Attrition Analysis

Predict employee attrition using machine learning and gain actionable insights through data visualization.

📌 Overview

This project helps HR departments predict which employees are likely to leave the organization and understand the key reasons behind attrition. By analyzing employee data and visualizing trends, companies can take timely action to improve retention.

👥 Team Members

• Hansa Pradhan
• Snehal Nivsarkar
• Sujata Rai
• Gursimran Singh

Supervised by: Dr. Jabir Ali, Assistant Professor
SRM Institute of Science & Technology

🔍 Problem Statement

Employee attrition is a costly and disruptive problem. Most organizations lack a data-driven approach to predict and mitigate turnover. This project leverages machine learning to forecast attrition risk and identify contributing factors.

🎯 Goals

• Predict probability of employee attrition using Random Forest
• Visualize important factors driving attrition
• Enable HR to take preventive actions
• Build a user-friendly interface for secure HR access

🧪 Methodology

1. Data Preprocessing

   • Cleaned and prepared HR dataset (~1700 records)
   • Created target labels for attrition

2. Modeling

   • Used Random Forest Classifier for prediction
   • Tuned hyperparameters for optimal accuracy
   • Analyzed feature importance

3. Visualization

   • Dashboards showing attrition risk and key metrics
   • Attrition List flagging high-risk employees

4. Interface

   • Login page for HR access
   • Navigation through dashboard, predictions, and survey forms

🖼️ Screenshots

🔐 Login Page

🧹 Data Processing Page

📋 Attrition List

📊 Feature Importance Graph

📈 Visual Representations (Dashboard)

⚙️ Tech Stack

• Language: Python
• Algorithm: Random Forest
• Visualization: Matplotlib, Seaborn
• IDE: Jupyter Notebook / Any Python IDE
• Libraries: pandas, scikit-learn, matplotlib, seaborn

Demo Video

zoom_0.mp4