Skip to main content

Guarding the Gateway: A Case Study on Fraud Prediction and Financial Crime Forensics in a Leading UK High Street Bank

Customer Context

The leading UK High Street Bank recognized the critical importance of risk assessment and fraud prevention in both its retail and corporate segments. Ensuring compliance, deterring fraud, and gaining insights into new clients and their activities were top priorities for the bank during the onboarding process. To achieve this, the bank aimed to build a comprehensive customer risk assessment tool that would implement various checks and strategies to identify potential threats among new and existing customers and their related links.

Key Business Challenges

The bank faced several challenges in implementing the Fraud Prediction & Financial Crime Forensics program:

  1. Legacy Platform: The existing platform lacked the agility and advanced analytics capabilities required for effective fraud prediction and financial crime forensics.
  2. Data Ecosystem: Building a new data and analytics ecosystem in-house required integrating various storage technologies, such as HDFS, Neo4J, MongoDB, and NuoDB, to handle diverse data sources.
  3. Risk Assessment Strategies: Designing and implementing a wide range of risk assessment strategies, including graph search and node prediction on Neo4J, required expertise in data science and advanced analytics.
  4. Compliance and Detection: Ensuring compliance with regulatory requirements and efficiently detecting suspicious activity, customer screening due diligence, and potential fraud were complex tasks.

Coforge Solution

Coforge, as the strategic technology partner in this transformation program, provided the following solutions to address the challenges:

  1. New Data & Analytics Ecosystem: Coforge designed and developed the Gen-II FCTP (Fraud & Financial Crime Transformation Program) by implementing a new data and analytics ecosystem with polyglot storage technologies.
  2. Data Science and Analytics: Advanced data science techniques, including graph search and node prediction on Neo4J, were leveraged to power the detection engine for suspicious activity reports and customer screening due diligence.
  3. Comprehensive Risk Assessment: The solution integrated a wide array of risk assessment strategies to identify potential threats and links between transactions and entities with predefined blacklists and gray lists.
  4. Agility and Efficiency: The new platform significantly improved agility in analyzing card transactions and identifying links with blacklisted entities, enabling faster response times to potential fraud cases.


The Fraud Prediction & Financial Crime Forensics program yielded substantial positive outcomes for the leading UK High Street Bank:

  1. Improved Detection and Analysis: The advanced analytics capabilities, especially on Neo4J, provided better insights into card transactions and links with blacklisted entities, resulting in improved fraud detection and financial crime prevention.
  2. Increased Agility: The implementation of the new data and analytics ecosystem led to enhanced agility in analyzing transactions and conducting risk assessments.
  3. License Cost Reduction: The bank achieved significant cost savings through a reduction in license costs associated with the legacy platform.
Let’s engage