Project 3 — HR Analytics Dashboard¶
Use data to answer the question that keeps every HR director awake: why are our best people leaving, and what can we do about it?
Overview¶
Employee attrition is expensive — replacing an employee costs 50-200% of their annual salary in recruitment, onboarding, and lost productivity. This project analyses an HR dataset to identify the drivers of attrition, the departments and roles most at risk, and the factors leadership can actually influence.
Business Objective¶
Reduce voluntary attrition by identifying the strongest predictors of employee departure and building a dashboard that helps HR proactively support at-risk employees before they resign.
Tools and Skills¶
| Tool | Used for |
|---|---|
| Excel | Initial exploration, pivot analysis |
| Python (Pandas) | Cleaning, feature engineering, correlation analysis |
| Power BI | Interactive HR dashboard |
| SQL | Attrition rate by segment queries |
Difficulty¶
Beginner-Intermediate — clean dataset, clear target variable. Good for practising segmentation and correlation analysis.
Dataset¶
- Source: IBM HR Analytics Employee Attrition
- Download: Kaggle IBM HR Analytics
- Size: 1,470 employees × 35 features
- Schema details: dataset-guide
Project Files¶
| File | Description |
|---|---|
| business-problem | Business context and questions |
| dataset-guide | Dataset schema and column descriptions |
| data-cleaning | Cleaning and feature engineering |
| sql-analysis | Attrition SQL queries |
| dashboard-design | Power BI HR dashboard design |
| insights-and-recommendations | Findings and HR recommendations |
| interview-questions | Project interview questions |
Learning Outcomes¶
- Analyse attrition rate across multiple dimensions
- Identify which factors correlate with employee departure
- Distinguish correlation from actionability (some drivers can't be changed)
- Build an HR dashboard that respects employee privacy
- Communicate sensitive findings to HR leadership