Objective

A large US-based bank wanted to standardize data processes, implementing and monitoring control check points to measure data quality for large scale migration of legacy risk management systems into a strategic system.

Challenges
 

• Lack of trust in data due to poor data quality and lack of data quality reporting.
  
• Siloed risk management in outdated legacy systems.
  

Approach
 

• Created an end-to-end control framework for data quality management.
  
• Established a scalable and standardized reporting framework and automated across 3 stages leveraging Python.
  
• Incorporated Machine Learning matching algorithms (fuzzy logic) using distance and ratio methodology to automate data quality checks.
  

Impact
 

• Increased data quality and built a reproducible framework for measuring and reporting DQ for future use.
  
• Overall automation resulted in a reduction of ~ 85% turn around time.
  

Questions

Looking for high-end research and risk services? Reach out to us at: