An interactive Power BI dashboard developed to analyze 148,671 loan applications and identify the key factors influencing loan approvals and defaults. The dashboard enables financial institutions to monitor portfolio health, evaluate borrower risk, and support data-driven lending decisions through advanced visualizations and DAX measures.
Financial institutions process thousands of loan applications, making it difficult to identify high-risk borrowers using raw data. The dataset contained inconsistent values, missing records, and unstructured information, limiting meaningful analysis and increasing the risk of inaccurate lending decisions.
Design a Power BI dashboard that:
- Cleans and transforms raw loan data
- Tracks loan approval and default performance
- Identifies high-risk customer segments
- Provides actionable insights for portfolio monitoring
- Supports strategic lending and risk management
- Imported 148,671 loan records
- Cleaned missing and inconsistent data using Power Query
- Standardized gender categories
- Converted loan status codes into readable values
- Calculated Loan-to-Value (LTV) and Debt-to-Income (DTI) ratios
- Created calculated columns and business metrics
- Developed DAX measures for:
- Default Count
- Approved Loan Count
- Approval Rate
- Portfolio KPIs
- Optimized the data model for better dashboard performance
Created interactive Power BI visuals including:
- 📌 Executive KPI Cards
- 🌳 Treemap (Loan Purpose vs Defaults)
- 📈 Scatter Plot (Credit Score vs Loan Approval)
- 🥧 Approval vs Default Pie Chart
- 📊 Regional Default Analysis
- 📉 Stacked Bar Chart (Approved vs Defaulted Loans)
- 🎛 Interactive Slicers for dynamic filtering
Analyzed loan performance based on:
- Credit Score
- Income
- Loan Purpose
- Region
- Gender
- Loan Status
- Portfolio Risk
- Successfully analyzed 148,671 loan applications
- Improved visibility into loan portfolio performance
- Identified high-risk loan purposes and regions
- Demonstrated the positive relationship between credit score and loan approval
- Enabled faster, data-driven lending decisions through interactive dashboards
- Built a scalable reporting solution suitable for banking and financial analytics
✅ Interactive Power BI Dashboard
✅ Dynamic KPI Monitoring
✅ DAX Calculations
✅ Loan Default Analysis
✅ Credit Risk Assessment
✅ Regional Performance Analysis
✅ Portfolio Health Monitoring
✅ Interactive Filters & Drill-down Analysis
- Microsoft Power BI
- Power Query
- DAX
- Microsoft Excel
- Data Cleaning
- Data Modeling
- Business Intelligence
- Total Loan Applications
- Approval Rate
- Default Rate
- Average Credit Score
- Total Loan Portfolio Value
- Approved Loans
- Defaulted Loans
- Higher credit scores significantly improve loan approval probability.
- Certain loan purposes contribute disproportionately to loan defaults.
- Loan defaults vary across geographical regions.
- Higher-income applicants generally exhibit lower default risk.
- Interactive filtering enables rapid portfolio exploration and supports better lending decisions.
📁 Loan-Default-Prediction-Dashboard
│
├── Dataset
├── Power BI Dashboard (.pbix)
├── Dashboard Screenshots
├── README.md
└── Documentation
This dashboard helps financial institutions:
- Reduce lending risk
- Improve credit evaluation
- Monitor portfolio performance
- Identify high-risk borrower segments
- Support strategic decision-making using business intelligence
Harendra
MBA (Business Analytics)
Power BI | SQL | Python | Excel | Business Intelligence
⭐ If you found this project useful, don't forget to Star the repository!