Banking Data Analysis

Banking Analytics Project Summary

This is an end-to-end banking analytics project combining Python, SQL, and Power BI to analyze customer demographics, deposits, loans, credit exposure, income, and loyalty segments for business insight generation.

Workflow

Raw Banking Data, Python Cleaning and EDA, SQL Business Analysis, Power BI Modeling, DAX Measures, Interactive Dashboard, Business Insights.

Tools Used

Python and Pandas for data cleaning and manipulation. Matplotlib and Seaborn for exploratory visualization. MySQL for business query analysis. Power BI and DAX for dashboard and KPI development.

Dashboard Structure, 3 Pages

1.Executive Summary. High-level KPIs covering Total Customers, Average Income, Total Deposits, Total Credit Exposure, Credit Card Balance, and Average Risk Weighting, plus visuals on gender, age, income, and nationality distribution, and a top-customer detail table for identifying high-value clients.

2.Customer Insights. Deeper demographic and behavioral analysis with KPIs on average age, male and female counts, and average loans. Visuals cover gender-by-age breakdowns, income category splits, income-by-age comparisons, loyalty tier distribution across Jade, Silver, Gold, and Platinum, and nationality concentration.

3.Financial Performance. Focuses on deposits, loans, savings and checking accounts, business lending, and credit card balances. KPIs include Bank Deposits, Credit Exposure, Savings, Personal Loans, Business Lending, and Credit Card Balance. Visuals compare deposits vs loans by age, savings by income, income vs savings trends, credit card exposure by age, and account type splits by income, including a scatter plot linking income to deposits.

Python EDA

Covered structure and type checks, missing and duplicate value handling, data cleaning, category creation, distribution analysis, demographic comparisons, and outlier detection to validate data before SQL and Power BI work.

SQL Analysis

Used aggregations, subqueries and CTEs, window and ranking functions, running totals, and segmentation to solve problems like identifying high-income customers with below-average deposits, measuring the percentage of deposits held by top customers, ranking nationalities by deposits within income tiers, and finding segments strong on deposits but weak on loans.

Key Business Insights

Seniors are the largest and most active customer segment. Mid-income customers dominate the base. Europeans are the largest nationality group. Deposit and loan activity concentrates among senior and middle-aged customers. Seniors carry the highest credit card balances. Higher income does not always mean higher savings. Loyalty tiers offer retention and upsell opportunities.

Interactive Features

Filters for Loyalty, Nationality, Age, Gender, and Occupation, a Reset button, and cross-filtering across visuals for dynamic exploration.

Outcome

Demonstrates full-stack analytics capability including data cleaning, EDA, SQL problem-solving, customer segmentation, financial analysis, visualization, and dashboard design. Authored by Anand Verma, Aspiring Data Analyst.
Project Workflow

1. Raw Banking Data
2. Python Data Cleaning and EDA
3. SQL Business Analysis
4. Power BI Data Modeling
5. DAX Measures and KPIs
6. Interactive Banking Dashboard
7. Business Insights

Project Outcome

This project demonstrates the ability to perform an end-to-end data analytics workflow using Python, SQL, and Power BI.

It shows skills in:
1. Data cleaning and pre-processing
2. Exploratory data analysis
3. SQL-based business problem solving
4. Customer segmentation
5. Financial performance analysis
6. Data visualization
7. Dashboard design
8. Business insight generation

Author

Anand Verma
Aspiring Data Analyst specializing in Python, SQL, Power BI, and Data Analytics