📌 Project Overview
This project presents an end-to-end credit risk analysis using a real-world style loan dataset.
The objective is to assess portfolio exposure, default risk, and borrower financial profiles, delivering actionable insights through a professional Power BI dashboard.
The project simulates a typical workflow used in banking and financial analytics roles, combining SQL-based data preparation with DAX-driven analytical modeling.
🧠 Business Questions Addressed
What is the overall size and exposure of the loan portfolio?
What percentage of loans are non-performing (NPL Rate)?
How does credit risk vary across different credit score bands?
Are non-performing loans associated with higher loan amounts?
How do income and debt levels differ between paid and defaulted loans?.
📊 Dashboard Overview
The Power BI dashboard is structured into four analytical sections:
Loan & Banking Portfolio Analysis
🔗 Project Links
Dashboard: (link / images)
1️⃣ Portfolio Overview
Total Loans
Median Loan Amount
Exposure at Risk
NPL Rate
3️⃣ Financial Profile Analysis
Average annual income vs. monthly debt by loan status
Comparison of repayment capacity
4️⃣ Loan Amount Analysis
Median loan amount by loan status
Identification of higher-risk exposure segments
2️⃣ Credit Risk Analysis
NPL Rate by Credit Band
Loan outcomes by credit quality (100% stacked bar)
🗂️ Dataset
Source: Loan & Banking dataset (cleaned and standardized)
Records: > 100,000 loans
Key features:
Loan status
Loan amount
Credit score
Annual income
Monthly debt
Credit history variables
🧹 Data Preparation (SQL Server)
All data preparation was performed in SQL Server, including:
Data cleaning and type normalization
Credit score normalization
Creation of analytical views
Removal of invalid and missing values
📄Project Summary
Click on the gallery to view the key insights from this project.
All data preparation was performed in SQL Server, including:cc