Transforming Banking Data into a $127M Risk Management SystemTransforming Banking Data into a $127M Risk Management System
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Mosaddek Hosen's avatar
Mosaddek Hosen Sajeeb
• May 5
I was tasked with transforming a massive dataset of 157,000+ banking transactions into a strategic early-warning system. The goal was to protect a $127M credit portfolio by identifying churn drivers and financial risk markers before they impacted the bottom line.
What I Delivered:
Automated Data Pipeline: Engineered a robust ETL process using Python to clean and validate 157k records for 100% reporting accuracy.
Risk Intelligence: Developed custom DAX algorithms to flag high-utilization rates (up to 479%) and track the $127.4M total debt across age and income segments.
Operational Audit: Isolated $56.9K in failed transactions, allowing the client to investigate technical and fraud-based leakage.
Client Health Scoring: Built a dynamic scoring system to categorize 2,000 clients into "Healthy" vs. "Risky" based on seniority and transaction success.
Tools & Skills
Power BI
SQL (PostgreSQL)
Python (Pandas/NumPy)
Financial Modeling
Data Engineering
Data VisualizationData AnalysisMicrosoft Power BI
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started