Objective

To support a leading US bank in its migration from a legacy risk management system to a new strategic platform by standardizing data, and implementing and monitoring a control framework to assess data quality.

Challenges

• Presence of multiple risk systems and inconsistent data feeds
• Existence of different naming conventions and formats 
• Ned to generate multiple reports per regulatory and internal requirement
• sNeed to maintain data granularity for reporting purposes

CRISIL's Solution

CRISIL followed a three-step end-to-end process for data standardization and quality enhancement:

1. Establishing Control Framework

• Gap Analysis - Analyzed the as-is process and identified pain points
  
• Data Sourcing - Identified sources and determine data that needs to be normalized
  

2. Data Analysis & Standardization

• Cluster Analysis - Identified and grouped data on the basis of underlying issues or patterns
  
• Machine Learning - Approximated string matching using fuzzy logic for data that could not be clustered
  
• Standardization - Standardized data across all products at various levels
  

3. Resolution & Reporting

• Reporting - Data quality issue summary reported to senior management
  
• Reports generated using BI tools to ensure data consistency
  
• Resolution - Identified and remediated causes of data quality issues by coordinating with technology partners
  

The CRISIL solution provided automation across three stages with Python, and incorporated machine learning matching algorithms (fuzzy logic) using distance and ratio methodology to automate data quality checks

Client Impact

• Created an end-to-end control framework for data quality management
  
• Established a scalable and standardized reporting framework for both internal use and regulatory requirements
  
• Overall automation resulted in throughput reduction of ~85% in terms of TAT
  

Questions

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