This project implements machine learning models to predict employee attrition using the IBM HR Analytics Employee Attrition dataset from Kaggle. The goal is to identify key factors that influence employee turnover and build predictive models to help HR professionals make data-driven decisions.
The dataset is sourced from 📊 Kaggle's IBM HR Analytics Employee Attrition & Performance. It includes:
- 👥 1,470 employee records
- 📑 35 features including demographics, job role, satisfaction levels
- 🎯 Target variable: Attrition (Yes/No)
ML_Gisma_Project/
├── 📂 data/
│ └── 📄 WA_Fn-UseC_-HR-Employee-Attrition.csv
├── 📓 employee_attrition_ML_project.ipynb
├── 📜 requirements.txt
└── 📖 README.md
pip install -r requirements.txt- 📊 Exploratory Data Analysis (EDA)
- 🏗️ Feature Engineering
- 🤖 Model Development & Evaluation
- 📈 Performance Metrics Analysis
1️⃣ Clone the repository:
git clone https://github.com/eshagarwal/ML_Gisma_Project.git
cd ML_Gisma_Project2️⃣ Install dependencies:
pip install -r requirements.txt3️⃣ Run the Jupyter notebook:
jupyter notebook employee_attrition_ML_project.ipynb📏 Model performance metrics 💡 Feature importance analysis 🔍 Insights derived from the analysis
This project is licensed under the Apache License - see the 📄 LICENSE file for details.
- 📊 Dataset provided by IBM HR Analytics Employee Attrition & Performance on Kaggle
- 🏢 Inspired by real-world HR analytics challenges