• Customer Risk Rating
  • Report
  • Financial Crime
  • AML
  • Banks
  • Enhanced Due Diligence
May 22, 2018

Machine learning for creating dynamic customer risk ratings

Does your risk rating process reflect true risk?

New banking methods have enabled customers to access and move their funds easily. However, this has also opened up ways for nefarious elements to transfer their ill-gotten gains across accounts, states and countries.


Financial institutions across the world are struggling to account for the risks posed by new and innovative ways of money laundering. New risk indicators need to be included in the anti-money laundering (AML) framework and necessary mitigation processes developed to ensure financial institutions follow the regulations.


A critical indicator is customer risk rating (CRR), which is a score or band assigned to a customer based on perceived financial-crime risk derived from parameters such as the customer’s residence, accounts, and product holdings.


But these static parameters do not always help establish the correct risk score because of factors such as frequency of change in customer behaviour, known associates, and transactional data. Additionally, some parameters may not vary with time, so customers could remain in the same risk band irrespective of their current behaviour. This is a significant drawback of the current CRR model, which could necessitate due-diligence and cause firms to focus on non-risky customers. Further, in the AML framework, this leads to higher false positive rates and impacts a firm’s operational aspects.


This white paper highlights the solutions for designing a CRR model that holistically captures the financial-crime risk of a customer.


To minimise the impact of the risks and problems mentioned above, we propose a dynamic customer risk rating or score, which is a consolidated risk number summarising a customer’s intrinsic risk to the bank and is updated on the basis of parameters, both static and dynamic.


This intrinsic risk is mainly captured through the customer’s transaction behaviour, and non-transactional attributes are determined through customer information file, past alerts data, network of past financial crime-related activities, and geospatial characteristics.