A data-driven Power BI project to analyze banking datasets, evaluate customer loan behavior, and identify financial risk patterns. The project delivers a multi-page interactive dashboard with KPIs and insights to support risk management and decision-making in the banking sector.
Analyzed a dataset of 10,000+ banking customers to assess loan repayment behavior and minimize lending risks. Developed a Power BI dashboard with three key pages: Loan Dashboard → Tracks loan amount, repayment, and client risk profiles. Deposit Dashboard → Monitors deposits by client type, account type, and income bands. Summary Dashboard → Consolidated KPIs showing overall financial performance and risk segmentation.
✅ 15+ KPIs across loans, deposits, and client engagement metrics.
✅ Risk Segmentation → Income-based and correlation-driven segmentation improved profiling accuracy by 20%.
✅ Dynamic DAX Measures such as SUM, SUMX, DISTINCTCOUNT, and DATEDIFF for real-time analytics.
✅ Interactive Visuals providing actionable insights into customer behavior and financial trends.
✅ Data Cleaning & Preparation using Power Query and DAX transformations for accurate reporting.
Power BI → Dashboard design, DAX calculations, data modeling, and visualization.
SQL / Excel → Data preprocessing, cleaning, and validation.
Power Query → Data transformation and calculated column creation.
Total Clients → Distinct count of customers.
Total Loan → Aggregate of bank loans, business lending, and credit card balances.
Total Deposit → Sum of deposits from savings, checking, and foreign accounts.
Total Fees → Processing and maintenance fee calculations.
Engagement Days → Client activity duration in the bank.
Income Band → Categorization of clients based on estimated income.
Banking-Risk-Analytics-Dashboard/ │ ├── Datasets/ # Raw and transformed datasets ├── Screenshots/ # Power BI dashboards photo ├── Report/ # Project Report └── README.md # Project documentation
💡 Customers in low-income segments had higher loan delinquency risk.
💡 Private banks showed a greater number of clients compared to public banks.
💡 Processing fees and loan amount correlation helped in identifying high-value risk customers.
💡 Foreign account deposits significantly influenced overall portfolio strength.
💡 Engagement length revealed strong relationships between customer loyalty and loan repayment patterns.
💡This project demonstrates the use of Power BI and data analytics to deliver insights that support financial decision-making and risk mitigation. It showcases strong skills in:
✅ Data analysis and transformation
✅ Business intelligence reporting
✅ KPI design and visualization
💡Integrate predictive models to forecast loan defaults.
💡Automate data refresh using scheduled Power BI gateways.
💡Expand dashboard to include geographical and demographic segmentation.
Mohd Fuzail Aspiring Data Analyst | SQL | Power BI | Excel | Python