💳 Credit Card Financial Risk Analysis

An end-to-end financial risk analytics solution built with Power BI, SQL, and DAX — delivering real-time insights into credit card transactions, customer behavior, and revenue performance.

---

🌐 Live Dashboard

🔴 Click the banner below to access the interactive Power BI dashboard live:

👉 Open Interactive Dashboard

⚠️ Access may require organizational credentials. The dashboard is hosted on Microsoft Power BI Service.

---

📋 Table of Contents

• Overview
• Live Dashboard
• Key Metrics & Insights
• Features
• Data Sources
• DAX Queries
• Project Insights
• Tech Stack
• Author

---

📌 Overview

This project presents a comprehensive Credit Card Financial Risk Analysis Dashboard built using Power BI, connected to a SQL database containing real-world-style transaction and customer data.

The dashboard empowers financial analysts, risk managers, and business stakeholders to:

• 📊 Monitor credit card revenue, transactions, and utilization in real time
• 🔍 Identify high-risk customer segments and delinquency patterns
• 📈 Track weekly and year-to-date performance trends
• 🌍 Analyze geographic and demographic revenue distribution

---

📊 Key Metrics & Insights

📅 Year-To-Date (YTD) Summary

Metric	Value
💰 Overall Revenue	$57M
💵 Total Interest Earned	$8M
🔄 Total Transaction Amount	$46M
👨 Male Customer Revenue	$31M
👩 Female Customer Revenue	$26M
💳 Blue & Silver Card Share	93% of transactions
🗺️ Top States (TX, NY, CA)	68% of revenue
✅ Overall Activation Rate	57.5%
⚠️ Overall Delinquent Rate	6.06%

📆 Week-Over-Week (WoW) Changes

Metric	Change
📈 Revenue Growth	+28.8%
🔄 Transaction Amount	Increased
👥 Customer Count	Increased

---

✨ Features

Feature	Description
🖥️ Interactive Dashboard	Fully interactive Power BI visuals with filters, slicers, and drill-throughs
⚡ Real-Time Insights	Connected to live SQL data for up-to-date reporting
🧮 Advanced DAX Measures	Custom DAX formulas for revenue, segmentation, and WoW calculations
👥 Customer Segmentation	Age group and income group classification for demographic analysis
🌍 Geographic Analysis	State-level revenue breakdown across the US
📉 Risk Monitoring	Delinquency and activation rate tracking for risk assessment
📊 Revenue Attribution	Breakdown by card category, gender, and transaction type

---

🗄️ Data Sources

📦 SQL Database
 ├── 📄 public.cust_detail   → Customer demographic & profile data
 └── 📄 public.cc_detail     → Credit card transaction & financial data

The data pipeline involves:

1. Data Ingestion — Raw data loaded into a PostgreSQL database
2. Data Transformation — Cleaned and structured using SQL queries
3. Data Modeling — Relationships built in Power BI data model
4. DAX Calculations — Custom measures for business KPIs

---

🧮 DAX Queries

👥 Customer Segmentation

AgeGroup = SWITCH(
    TRUE(),
    'public cust_detail'[customer_age] < 30, "20-30",
    'public cust_detail'[customer_age] >= 30 && 'public cust_detail'[customer_age] < 40, "30-40",
    'public cust_detail'[customer_age] >= 40 && 'public cust_detail'[customer_age] < 50, "40-50",
    'public cust_detail'[customer_age] >= 50 && 'public cust_detail'[customer_age] < 60, "50-60",
    'public cust_detail'[customer_age] >= 60, "60+",
    "unknown"
)

IncomeGroup = SWITCH(
    TRUE(),
    'public cust_detail'[income] < 35000, "Low",
    'public cust_detail'[income] >= 35000 && 'public cust_detail'[income] < 70000, "Med",
    'public cust_detail'[income] >= 70000, "High",
    "unknown"
)

📅 Time Intelligence

week_num2 = WEEKNUM('public cc_detail'[week_start_date])

💰 Revenue Measures

Revenue = 
    'public cc_detail'[annual_fees] 
    + 'public cc_detail'[total_trans_amt] 
    + 'public cc_detail'[interest_earned]

Current_week_Revenue = CALCULATE(
    SUM('public cc_detail'[Revenue]),
    FILTER(
        ALL('public cc_detail'),
        'public cc_detail'[week_num2] = MAX('public cc_detail'[week_num2])
    )
)

Previous_week_Revenue = CALCULATE(
    SUM('public cc_detail'[Revenue]),
    FILTER(
        ALL('public cc_detail'),
        'public cc_detail'[week_num2] = MAX('public cc_detail'[week_num2]) - 1
    )
)

---

💡 Project Insights

🔄 Week-Over-Week Performance

• 📈 Revenue jumped by 28.8% compared to the previous week
• 🔄 Transaction amounts and counts showed positive growth
• 👥 Customer engagement increased week-over-week

📆 Year-To-Date Highlights

• 💰 Total revenue reached $57 Million
• 🏦 Interest income contributed $8 Million
• 💳 Transaction volume totaled $46 Million
• 👨‍💼 Male customers drove 54% of revenue ($31M vs $26M female)
• 💳 Blue & Silver cards dominate with 93% of all transactions
• 🗺️ Texas, New York & California account for 68% of total revenue
• ✅ Card activation rate stands at 57.5%
• ⚠️ Delinquency rate tracked at 6.06% — a key risk indicator

---

🛠️ Tech Stack

Technology	Purpose
	Dashboard & Visualization
	Data Storage & Querying
	Business Metrics & KPI Calculations
	Data Transformation

---

👤 Author

ABDELAALI ENNAMAT

Data Analyst | Business Intelligence | Power BI Developer

---

⭐ If you found this project useful, please consider giving it a star! ⭐