Nationwide reduces fraud losses by 75%

The world's largest building society uses SAS® in its strategic project to tackle a variety of fraud

Nationwide is the world's largest building society and the UK's largest mutual, with 700 branches across the country. A perennial activity for Nationwide, as for other banks and building societies, is the fight against fraud.

Nationwide wanted to lower its fraud losses. In order to achieve this, a strategic project and a fraud analytics team were established within the organisation to tackle the problem. Nationwide chose SAS® to support this strategic project.

"SAS has contributed towards a 75% reduction in fraud losses, to a quarter of their peak a couple of years ago," says David Parsons, Senior Manager Fraud Analytics at Nationwide. "That is a real, bottom-line saving that we are making."

SAS has contributed towards a 75% reduction in fraud losses, to a quarter of what they were at their peak a couple of years ago. That is a real, bottom-line saving that we are making.

David Parsons
Senior Manager Fraud Analytics at Nationwide

Business rules identify multiple types of fraud

Using SAS, Nationwide built ten fraud detection rule sets to identify fraudulent activity across Nationwide's operations. These rules monitor: account takeover; money laundering; employee fraud; cheque credit; intercepted chequebooks; vulnerable customers; investment fraud; solicitors; Nationwide's regional brands; and credit card tactical solutions.

Nationwide's fraud analytics team runs data from five sources, such as a financial crimes database and existing corporate data, through the business rule sets, which then flags transactions or other records to examine more closely. This is particularly important in anti-money laundering efforts, where this analysis is a regulatory requirement, and in cases of high-risk fraud, such as account takeover and employee fraud.

These rule sets and automated queries mean that Nationwide can better protect its customers against fraud: for example, an elderly customer wanted to invest in a company, and came into a Nationwide branch to make a £5,000 transfer. An intra-day fraud check, which is an automated query that is part of Nationwide's standard rule set in SAS, identified that the company was disreputable and named on various watch lists. This information was imparted to the customer who, in turn, chose to block the payment before it cleared and thus was not defrauded of £5,000.

Ad hoc queries made simple

In addition, Nationwide is able to run ad hoc queries: it's possible to simply run the data using SAS® Enterprise Guide® and examine the analysis it produces. The ability to make ad hoc enquiries has made it possible to identify and uncover fraud that Nationwide wouldn't have been able to find before. The system gives Nationwide flexibility in its fraud analysis, because the graphical user interface of SAS Enterprise Guide means members of the fraud analytics team can simply point and click to run a query, rather than writing code. "SAS is now our tool of choice for a lot of our fraud detection," says David Parsons.

Creating predictive models to support anti-money laundering projects

To support Nationwide's anti-money laundering initiatives, the SAS system provides analysis that flags dubious transactions, using information about past behaviour to build 'transaction profiles' for customers. If transactions start to fall within the pattern of behaviour identified, the transaction is identified as suspicious.

Nationwide now receives regular visits from its fraud-fighting peers at other institutions who wish to tighten their approach.

Rapid reporting across the organisation

Nationwide is not only using SAS to detect fraud, but also to report on it. Where, previously, reporting would have involved pulling information from various sources into a spreadsheet, using SAS® Information Portal, Nationwide Fraud Team can provide self-service reporting. For example, the fraud analytics team has created a report detailing fraud losses versus planned losses, broken down by fraud type and by product, which is automated and runs every day so management can refine their efforts to combat financial crime.

Using SAS Information Portal and SAS® Web Report Studio, both part of SAS® Enterprise BI solution, the fraud analytics team can also share reports with the team and with others within Nationwide who need this information. For example, Nationwide has been able to respond to the postal interception of chequebooks, with the end-user investigations team utilising reports from SAS Web Report Studio to spot certain suspect characteristics. The easy-to-interpret reports mean the investigations team can pinpoint postal hotspots as they occur, without the need for detailed technical training or the use of other systems.

Looking to the future, Nationwide is interested in a move to the SAS® Fraud Framework which would help provide an integrated approach to fraud analytics and enable greater auditability, accountability, consistency, compliance and governance, all managed through a single framework. It will also allow for greater automation.

Nationwide is also examining how it can further use SAS in its anti-money laundering work, building its own rules for anti-money laundering, and using SAS® Enterprise Miner™ to build predictive models to support these rules. Nationwide is also looking to expand its use of SAS® BI tools as a search engine for its case management system.

 

Nationwide Logo

Challenge

Nationwide faced significant and escalating fraud losses, and needed a system to help detect and report on this more effectively.

Solution

Benefits

  • Improved fraud detection and reporting.
  • Significant contribution to reduction of losses through fraud by 75% since peak losses.
  • Effective anti-money laundering regulatory compliance.
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.