AI Case Study

NatWest Bank prevents over £7m worth of corporate fraud by using machine learning to detect suspicious invoice payment activity

NatWest has partnered with Vocalink Analytics to create and deploy a fraud detection system which works by analysing historic payment data to spot new potentially fraudulent payments. The system focuses on invoice payment redirection, which it claims has avoided making over £7M in fraudulent payments.

Industry

Financial Services

Banking

Project Overview

"Vocalink Analytics and NatWest worked together to develop, test and launch Corporate Fraud Insights, which identifies and flags suspicious non-real time payments. The system is designed to detect and prevent invoice redirection fraud - where businesses are duped into paying money into a fraudster’s account rather than to their intended supplier."

Reported Results

"Over £7m in false payments prevented".

Technology

Machine learning; "the company applies sophisticated analytical techniques to vast amounts of payments data to build models that can identify suspicious activity. Every time a business pays an invoice, a behavioural signature is left behind. By analysing these signatures, and the signatures of historical frauds, we are able to identify and flag suspected incidents".

Function

Risk

Audit

Background

"'Detecting invoice redirection fraud is akin to finding a needle in a haystack, as there are tens of millions of legitimate non-real-time payments every day,” said Lee Fitzgerald, head of fraud for Commercial and Private Banking at NatWest. 'But while the volume of fraud is relatively low, the values are typically large, so the business impact of this type of fraud can be crippling... Corporate Fraud Insights is part of our ongoing commitment to fighting payments-related fraud on behalf of our customers, helping businesses to stay safe and secure'".

Benefits

Data

Historic transaction data