📊 Workforce Intelligence – HR Analytics Dashboard

An end-to-end HR Analytics and Workforce Intelligence project that analyzes employee attrition using Python, SQL Server, T-SQL, Power BI, and DAX.

The project transforms raw employee data into meaningful workforce insights through exploratory data analysis, SQL-based data processing and validation, business analysis, and an interactive Power BI dashboard.

📌 Overview

Employee attrition is an important workforce metric that can help organizations understand workforce stability and identify employee segments with higher observed attrition.

This project analyzes attrition across key workforce dimensions such as tenure, overtime, salary, job satisfaction, work-life balance, department, and job role.

The project follows an end-to-end analytics workflow:

Exploratory Data Analysis using Python
SQL Server database setup
Data loading and validation
SQL-based business analysis
Power BI data modeling
DAX KPI calculations
Interactive workforce dashboard
Workforce attrition insights

⭐ Project Highlights

👥 Workforce & Employee Analysis
🚪 Employee Attrition Analysis
📉 Attrition Rate Calculation
🐍 Python Exploratory Data Analysis
🗄️ SQL Server Database
💾 T-SQL Business Analysis
🔍 Data Validation
📊 Power BI Dashboard
📐 DAX Measures & KPIs
📅 Tenure Analysis
⏰ Overtime Analysis
💰 Salary Analysis
😊 Job Satisfaction Analysis
⚖️ Work-Life Balance Analysis
🏢 Department Analysis
💼 Job Role Analysis

📸 Dashboard Preview

Workforce Intelligence – HR Analytics Dashboard

💼 Business Problem

Organizations collect employee information across departments, job roles, compensation, tenure, overtime, satisfaction, and other workforce attributes.

However, raw employee records make it difficult to quickly identify patterns in employee attrition.

This project provides an analytical solution to answer questions such as:

What is the overall employee attrition rate?
Which workforce segments show higher observed attrition?
How does attrition vary across employee tenure?
Do overtime employees show higher observed attrition?
Does lower salary correspond with higher observed attrition?
How does job satisfaction relate to observed attrition?
How does work-life balance relate to observed attrition?
Which departments and job roles show comparatively higher attrition?

The goal is to transform employee-level data into a clear and interactive workforce intelligence solution.

🎯 Project Objectives

Analyze employee attrition patterns.
Calculate the overall attrition rate.
Identify higher-attrition workforce segments.
Analyze attrition across tenure bands.
Compare overtime and non-overtime employees.
Analyze salary-based attrition patterns.
Examine job satisfaction and attrition.
Examine work-life balance and attrition.
Compare departments and job roles.
Build an interactive Power BI dashboard.
Present workforce findings in a business-friendly format.

🔄 Analytics Workflow

                 Raw Employee Dataset
                          │
                          ▼
                Exploratory Data Analysis
                          │
                          ▼
                    Data Preparation
                          │
                          ▼
                  SQL Server Database
                          │
                          ▼
                   Data Loading
                          │
                          ▼
                    Data Validation
                          │
                          ▼
                 Business Analysis
                          │
                          ▼
                Power BI Data Model
                          │
                          ▼
                    DAX Measures
                          │
                          ▼
              Interactive HR Dashboard
                          │
                          ▼
                 Workforce Insights

🛠️ Tech Stack

Category	Technology
🐍 Programming Language	Python
📊 Data Analysis	Pandas
📓 Notebook	Jupyter Notebook
🗄️ Database	Microsoft SQL Server
💾 Query Language	T-SQL
📈 Business Intelligence	Power BI
📐 Analytical Calculations	DAX
🔄 Version Control	Git
☁️ Repository Hosting	GitHub

📂 Project Structure

workforce-intelligence-hr-analytics/
│
├── data/
│   └── raw/
│       └── WA_Fn-UseC_-HR-Employee-Attrition.csv
│
├── notebooks/
│   └── 01_Exploratory_Data_Analysis.ipynb
│
├── powerbi/
│   └── Workforce_Intelligence_HR_Analytic.pbix
│
├── sql/
│   ├── 01_database_schema.sql
│   ├── 02_data_loading.sql
│   ├── 03_data_validation.sql
│   └── 04_business_analysis.sql
│
├── .gitignore
├── LICENSE
├── README.md
└── requirements.txt

📁 Dataset

The project uses the IBM HR Analytics Employee Attrition & Performance dataset.

The dataset contains employee-level information covering areas such as:

Employee demographics
Department
Job role
Job level
Monthly income
Overtime
Job satisfaction
Work-life balance
Years at company
Employment attributes
Attrition

The raw dataset is stored at:

data/raw/WA_Fn-UseC_-HR-Employee-Attrition.csv

🐍 Exploratory Data Analysis

Exploratory Data Analysis is performed using Python, Pandas, and Jupyter Notebook.

The EDA process is used to understand the dataset before SQL-based analysis.

Key activities include:

Dataset structure inspection
Data type checks
Missing-value analysis
Duplicate checks
Employee distribution analysis
Attrition distribution
Numerical analysis
Categorical analysis
Workforce segmentation
Initial attrition analysis

The notebook is available at:

notebooks/01_Exploratory_Data_Analysis.ipynb

🗄️ SQL Server Workflow

The SQL component processes and analyzes the employee dataset using Microsoft SQL Server and T-SQL.

The workflow is organized into four scripts.

1. Database Schema

sql/01_database_schema.sql

Creates the database structure required for the project.

2. Data Loading

sql/02_data_loading.sql

Loads the employee dataset into the SQL Server environment.

3. Data Validation

sql/03_data_validation.sql

Performs data-quality and consistency checks before analysis.

4. Business Analysis

sql/04_business_analysis.sql

Contains SQL queries used to analyze employee attrition and workforce segments.

📊 Power BI Dashboard

The final reporting layer is built using Microsoft Power BI.

The dashboard combines workforce KPIs and employee segmentation into an interactive analytical interface.

Power BI file:

powerbi/Workforce_Intelligence_HR_Analytic.pbix

The dashboard focuses on:

👥 Workforce size
🚪 Attrition
📉 Attrition rate
📅 Tenure
⏰ Overtime
💰 Salary
😊 Job satisfaction
⚖️ Work-life balance
🏢 Department
💼 Job role

📐 DAX & KPI Analysis

DAX measures are used in Power BI to calculate workforce metrics dynamically.

Key analytical measures include:

Total Employees
Employees Who Left
Attrition Rate
Segment-level Attrition Rate

These measures allow dashboard visuals and KPIs to respond dynamically to report interactions and filters.

📈 Key Workforce Findings

The analysis identified several workforce segments with comparatively higher observed attrition.

Workforce Segment	Employees	Employees Left	Observed Attrition Rate
📅 Early Tenure (0–1 Years)	215	75	34.88%
⚖️ Low Work-Life Balance	80	25	31.25%
⏰ Overtime Employees	416	127	30.53%
💰 Low Salary (< 3K)	395	113	28.61%
😊 Low Job Satisfaction	289	66	22.84%

The overall workforce baseline is:

Metric	Value
👥 Total Employees	1,470
🚪 Employees Who Left	237
📉 Overall Attrition Rate	16.12%

💡 Business Insights

The analysis highlights several areas that could be investigated further:

📅 Early Tenure

Employees with 0–1 years of tenure recorded the highest observed attrition rate among the analyzed segments.

⏰ Overtime

Employees working overtime showed a substantially higher observed attrition rate than the overall workforce baseline.

⚖️ Work-Life Balance

The lower work-life balance segment also showed elevated observed attrition.

💰 Salary

Employees in the lower-salary segment recorded a higher observed attrition rate compared with the overall workforce.

😊 Job Satisfaction

Lower job satisfaction was associated with a comparatively higher observed attrition rate in the dataset.

These findings can help identify workforce areas that may deserve deeper HR investigation.

⚠️ Analytical Disclaimer

The results represent observed relationships within the available dataset.

A higher attrition rate within a particular segment does not prove that the corresponding characteristic causes employees to leave.

For example, the higher observed attrition among overtime employees does not establish that overtime itself causes attrition.

The findings should therefore be treated as exploratory workforce insights and a starting point for further analysis.

🚀 Installation & Setup

1. Clone the Repository

git clone https://github.com/harsh8767/Workforce-Intelligence-HR-Analytics.git

2. Navigate to the Project

cd Workforce-Intelligence-HR-Analytics

3. Create a Virtual Environment

Windows

python -m venv venv
venv\Scripts\activate

Linux / macOS

python3 -m venv venv
source venv/bin/activate

4. Install Dependencies

pip install -r requirements.txt

▶️ Running the Project

Python EDA

Open:

notebooks/01_Exploratory_Data_Analysis.ipynb

Run the notebook using Jupyter Notebook or JupyterLab.

jupyter notebook

SQL Analysis

Execute the SQL scripts in this order:

01_database_schema.sql
        ↓
02_data_loading.sql
        ↓
03_data_validation.sql
        ↓
04_business_analysis.sql

These scripts create the database environment, load the data, validate the dataset, and perform workforce analysis.

Power BI Dashboard

Open:

powerbi/Workforce_Intelligence_HR_Analytic.pbix

using Power BI Desktop.

If required, update the SQL Server data-source connection and refresh the data model.

🧪 Data Validation

Data validation is performed before business analysis to improve confidence in the analytical results.

The validation process includes checks for:

Record counts
Missing values
Duplicate records
Data consistency
Key fields
Attribute values

Validation logic is available in:

sql/03_data_validation.sql

🚀 Future Improvements

Potential future enhancements include:

📈 Attrition trend analysis
🤖 Machine learning-based attrition prediction
👥 Employee segmentation
📊 Advanced HR KPIs
🔍 Power BI drill-through pages
📅 Monthly and yearly attrition analysis
📱 Power BI mobile layout
☁️ Power BI Service deployment
⚡ Automated data refresh
🔐 Row-level security

🙏 Acknowledgements

This project was developed using:

Python
Pandas
Jupyter Notebook
Microsoft SQL Server
T-SQL
Microsoft Power BI
DAX
Git
GitHub

👨‍💻 Developer

Harsh Chavan

Passionate about Data Analytics, Business Intelligence, SQL, Power BI, Python, Machine Learning, and Artificial Intelligence.

📫 Connect With Me

GitHub

https://github.com/harsh8767

LinkedIn

https://www.linkedin.com/in/harsh-chavan-1646a2257/

📜 License

This project is licensed under the MIT License.

See the LICENSE file for more information.

⭐ Support

If you found this project useful:

⭐ Star the repository
🍴 Fork the repository
💡 Share your feedback
🐛 Report issues
🚀 Suggest improvements

📌 Project Summary

Workforce Intelligence – HR Analytics demonstrates an end-to-end HR analytics workflow:

Raw Employee Data
       ↓
Python EDA
       ↓
SQL Server
       ↓
Data Validation
       ↓
Business Analysis
       ↓
Power BI + DAX
       ↓
Workforce Insights

The project demonstrates practical skills in data analysis, SQL, database processing, business intelligence, DAX, data visualization, and workforce analytics.

The final dashboard transforms employee-level data into an interactive view of attrition patterns and workforce segments, providing a foundation for data-driven HR analysis.

Thank You for Visiting This Repository! 👋

If you found the project useful, don't forget to ⭐ the repository.

Happy Learning & Analyzing! 🚀

Name		Name	Last commit message	Last commit date
data/raw		data/raw
images		images
notebooks		notebooks
powerbi		powerbi
sql		sql
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
requirements.txt		requirements.txt

Latest commit

History

Folders and files

Repository files navigation