📊 Retail Performance Intelligence Platform

An end-to-end Retail Data Analytics project that transforms nearly 10,000 retail transactions into actionable business insights using Python, Pandas, SQLite, SQL, and Power BI.

The project demonstrates a complete analytics workflow—from raw data preprocessing and SQL-based business analysis to automated reporting and interactive Power BI dashboards.

---

📌 Project at a Glance

• 📄 9,994 Retail Transactions
• 🧠 80+ SQL Queries
• 📊 3 Interactive Power BI Dashboard Pages
• 🐍 Automated Data Processing using Python & Pandas
• 🗄️ SQLite Database for Business Analytics
• 📈 Executive KPI Reporting & Interactive Visualizations

---

🚀 Project Highlights

• 📊 Interactive 3-page Power BI Dashboard
• 🐍 Automated data cleaning using Python & Pandas
• 🗄️ SQLite database for efficient SQL querying
• 🧠 80+ SQL queries covering beginner to advanced concepts
• 📈 Executive KPI reporting and business analytics
• 👥 Customer, Product, Sales & Regional performance analysis
• 📁 Clean, documented and portfolio-ready project structure

---

🖥️ Dashboard Preview

Executive Dashboard

Provides an executive overview of the business including revenue, profit, orders, regional sales performance and sales trends.

---

Customer & Product Insights

Analyzes customer purchasing behaviour, customer growth, customer segmentation, top customers and regional customer distribution.

---

Product & Regional Performance

Highlights category performance, top-selling products, regional profitability and product-level sales insights.

---

💼 Business Problem

Retail businesses generate thousands of transactions every day. Converting this raw transactional data into meaningful insights is essential for improving profitability, understanding customer behaviour, identifying high-performing products and supporting data-driven business decisions.

This project simulates a real-world analytics workflow by transforming raw retail data into interactive dashboards and business reports.

---

📂 Dataset

The project uses the Sample Superstore dataset.

Attribute	Value
Records	9,994
Features	27
Time Period	2014 – 2017
Regions	4
States	49
Customer Segments	3
Categories	3
Sub-Categories	17

---

🛠️ Technology Stack

Technology	Purpose
Python	Data Processing
Pandas	Data Cleaning & Transformation
NumPy	Numerical Operations
SQLite	Database Management
SQL	Business Analysis
Power BI	Dashboard Development
Matplotlib	Data Visualization
Git	Version Control
GitHub	Project Hosting

---

🔄 Project Workflow

                 Raw CSV Dataset
                        │
                        ▼
         Data Cleaning (Python + Pandas)
                        │
                        ▼
             SQLite Database Creation
                        │
                        ▼
             SQL Business Analysis
                        │
                        ▼
          Business Reports & KPIs
                        │
                        ▼
        Interactive Power BI Dashboard

---

📁 Repository Structure

Retail_Analytics/
│
├── assets/
│   ├── charts/
│   └── screenshots/
│
├── dashboard/
│   └── Retail_Performance_Dashboard.pbix
│
├── data/
│   ├── raw/
│   ├── processed/
│   └── retail.db
│
├── reports/
│
├── scripts/
│
├── sql/
│
├── README.md
├── LICENSE
├── requirements.txt
└── main.py

---

📈 Key Features

Data Preparation

• Cleaned and transformed raw retail transaction data
• Standardized data types and formats
• Generated analytical fields for reporting
• Exported cleaned datasets for downstream analysis

SQL Analytics

• 80+ SQL queries ranging from beginner to advanced
• Customer analysis
• Product performance analysis
• Sales trend analysis
• Regional profitability analysis
• Window Functions
• Common Table Expressions (CTEs)
• Ranking Functions
• KPI reporting

Power BI Dashboard

The project includes a three-page interactive dashboard:

1. Executive Dashboard

• Revenue
• Profit
• Orders
• Profit Margin
• Sales Trend
• Regional Sales
• Sales by Segment

2. Customer & Product Insights

• Customer Growth
• Top Customers
• Revenue per Customer
• Average Order Value
• Customer Segmentation
• Regional Customer Distribution

3. Product & Regional Performance

• Sales by Category
• Sales by Sub-Category
• Top Selling Products
• Regional Profitability
• Interactive Filters

---

📊 Business Insights Generated

The analysis answers several real-world business questions, including:

• Which regions generate the highest revenue?
• Which regions are the most profitable?
• Which customer segment contributes the most sales?
• Who are the highest-value customers?
• Which products generate the highest revenue?
• Which product categories perform the best?
• How has sales performance changed over time?
• Which regions require improvement?
• What are the overall business KPIs?

---

▶️ Getting Started

Clone the repository

git clone https://github.com/BibsAFK/retail-analytics.git

Move into the project directory

cd retail-analytics

Install dependencies

pip install -r requirements.txt

Run the analytics pipeline

python main.py

---

📚 Skills Demonstrated

• Data Cleaning
• Data Wrangling
• Exploratory Data Analysis (EDA)
• SQL Query Writing
• Advanced SQL
• SQLite Database Management
• Python Automation
• KPI Development
• Business Intelligence
• Power BI Dashboard Development
• Data Visualization
• Git & GitHub

---

🚀 Future Improvements

• Forecast future sales using Machine Learning
• Customer segmentation using clustering algorithms
• PostgreSQL integration
• Automated ETL pipeline
• Cloud deployment
• Interactive web-based analytics portal

---

👤 Author

Bibin

Computer Science Graduate | Aspiring Data Analyst

---