An end-to-end data analytics project that explores banking customer behavior, loans, deposits, and financial performance using real-world structured data.
Built with Power BI, Python (Pandas/NumPy/Matplotlib), and SQL, this project transforms raw banking data into actionable business insights.
📸 Screenshots
- Overview of total clients, loans, deposits, and accounts
-
- Loan distribution by income band, occupation, and banking relationship
-
- Deposit trends by income group, nationality, and relationship type
-
- High-level KPIs and performance metrics
-
- Uses Power BI Q&A feature for instant insights
-
✨ Project Highlights
| Metric | Value | Description |
|---|---|---|
| Total Clients | 1.5K+ | Total number of banking customers |
| Total Loan | 4.38bn | Total loan amount issued |
| Total Deposit | 3.77bn | Total deposits across accounts |
| Business Lending | 2.60bn | Loans given to businesses |
| Checking Accounts | 963.28M | Total checking account balance |
| Saving Accounts | 698.73M | Total savings balance |
| Foreign Currency | 45.02M | International account holdings |
🔍 Key Insights
- 📈 High Loan Concentration in specific Banking Relationships (Commercial & Institutional)
- 💰 Deposits are highest in medium-income customers
- 👩 Gender-based analysis shows variation in loan and deposit behavior
- 🌍 Nationality trends highlight key revenue-generating segments
- 💼 Business lending dominates overall loan portfolio
- 📊 Customer engagement strongly linked with deposits + loans combined
🔄 Workflow
- Imported structured banking dataset (multiple tables)
- Removed duplicates and handled missing values
- Standardized column names and formats
- Created derived columns:
- Total Loan
- Total Deposit
- Engagement Score
- Used Pandas & NumPy for data manipulation
- Performed:
- Distribution analysis
- Trend identification
- Outlier detection
- Joined multiple tables
- Created relationships and aggregations
- Optimized queries for reporting
- Designed interactive dashboards with:
- KPI Cards
- Bar Charts
- Donut Charts
- Filters (Gender, Year, Banking Relationship)
- Identified high-value customers
- Analyzed loan vs deposit patterns
- Segmented customers based on behavior
🛠️ Tech Stack
| Layer | Tools / Technologies |
|---|---|
| Data Processing | Python (Pandas, NumPy) |
| Data Analysis | Python, SQL |
| Visualization | Power BI |
| Database | SQL |
| Storage | Excel / CSV |
| Version Control | Git, GitHub |
🚀 Getting Started
Prerequisites:
- Power BI Desktop
- Python 3.8+
- SQL (MySQL / PostgreSQL / SQL Server)
git clone https://github.com/Vedant-Kharwade📌 Features
- Interactive filtering (Year, Gender, Banking Type)
- Clean UI with professional layout
- Real-time KPI tracking
- Multi-dashboard navigation
- Business-focused insights
Project Link:
https://github.com/Vedant-Kharwade/Banking-Analysis-Project-MS-SQL-Python-Power-Bi-
📬 Contact
🔗 https://www.linkedin.com/in/vedant-kharwade-45b82224b/
⭐ If you found this project useful, consider giving it a star!