Employee Attrition & Workforce Risk Analysis 📉

📌 Project Overview

Analyzed a dataset of 1,470 employee records (IBM HR Analytics) to identify key drivers of workforce turnover. The goal is to provide data-driven insights for HR and Operations teams to optimize retention strategies.

🛠 Tools Used

• Python: Pandas (Data Cleaning & GroupBy Analysis), Matplotlib/Seaborn (Visualization)
• Jupyter Notebook: Data processing pipeline

🔍 Key Findings

1. Overtime: Employees working frequent overtime have a ~30% attrition rate (vs 10% for non-overtime), making it the strongest predictor of turnover.
2. Department Risk: The Sales Department shows the highest attrition (>20%).
3. Income: Low-income employees show significantly higher flight risk compared to mid-to-high income bands.

📊 Code

Please check the .ipynb file in this repository for the full analysis code and visualization charts.

---

Author: Youzhi Liu