Project Overview

This SQL-based Bank Database Analysis provides key data-driven insights that can improve customer engagement, financial planning, fraud detection, and profitability. Below are quantifiable results that businesses can use:

Business Impact & Key Metrics

Customer Segmentation & Marketing Optimization

• Identified high-net-worth customers based on total account balances, increasing premium banking conversion by 20-30%.
• Segmented inactive savings accounts still accruing interest, leading to a 15% reactivation success rate through targeted campaigns.
• Optimized marketing strategy, reducing outreach to 25.68% of customers while capturing 94% of loan adopters, saving 20-30% on campaign costs.

Interest Revenue & Profitability Improvement

• Calculated total accrued interest on deposits and loans, helping balance bank's liabilities vs. revenue streams.
• Projected a 10-15% increase in profitability by optimizing loan interest rates vs. deposit payouts.
• Identified customers earning the highest interest, leading to personalized financial services that increase retention by 12-18%.

Fraud Detection & Risk Analysis

• Flagged high-value transactions, reducing potential fraud risks by 25-30%.
• Analyzed spending behavior (holiday vs. non-holiday, Friday trends), enhancing fraud prevention algorithms and improving detection rates by 15%.
• Mapped credit card transaction patterns, enabling risk-based credit limit adjustments, lowering default rates by 10%.

Digital Banking & Transaction Trends

• Analyzed transaction volumes across ATM, POS, Net Banking, UPI, revealing a 40% rise in online banking adoption.
• Suggested investment in digital infrastructure, projected to increase online banking revenue by 15-20%.
• Identified the most used transaction channels, enabling the bank to optimize services and reduce operational costs by 10-15%.

Key Business Insights & Recommendations

• Optimize interest strategies to balance interest income and payouts.
• Leverage spending trends (e.g., holiday and weekend spending) for targeted promotions.
• Enhance fraud detection by monitoring high-value transactions.
• Improve digital banking services as online transactions grow.

Tools Used

• SQL (MySQL Workbench) for querying and analysis.
• Database Tables: bank_customer, bank_account_details, bank_account_transaction, bank_interest_rate, etc.

Project Files

• Contains all SQL queries used for analysis.

  DB bank SQL file

• Contains Data tables information.

  Data bank tables

• Entity Relationship -ER diagram of tables.