Procurement fraud occurs when a company offers goods or services but either fails to deliver, under delivers or rigs the process against the rules to gain an advantage over competitors. Some common forms of procurement fraud include bribery, bid-rigging, embezzlement and submission of false claims. This is especially concerning when you are talking about business to government procurement, considering that money comes straight from the taxpayer. Government needs to find better ways to protect itself from this type of fraud.
Fighting procurement fraud
In recent years, fraud experts have turned to a hybrid analytical approach to fraud monitoring that incorporates both solid business best practices and advanced analytics to greatly reduce the amount lost due to fraud.
First and foremost, government agencies need to start by following good business rules. While these rules are likely already in place, sometimes a good reminder to procurement officials can be helpful. A couple examples of business rules include:
- If bidders show up on a disbarred list, don’t give them a contract. It may sound simple, but it is a rule that agencies sometimes fail to follow.
- Watch for too many invoices coming in on the same day. Take the time to check out each one thoroughly as fraudsters hope the volume of work leads to things being overlooked.
Advanced analytics can help agencies not only find cases of fraud, but also identify larger trends by analyzing the available data in different ways. By incorporating advanced analytics into a comprehensive fraud detection and investigation program, agencies can have the added benefit of the following:
Anomaly detection. This looks for behaviors that are unusual or unexpected. Historical anomaly detection looks at changes in behavior over time. If the system sees a sudden, drastic shift from historical patterns — with nothing to explain it — that piece of information will get flagged.
Anomaly detection also includes peer grouping or clustering. These techniques compare behavior to what is considered normal for a similar peer group and identifies behaviors that are different for that type of procurement. Finally, anomaly detection can profile the typical attributes of “good guys” and “bad guys.” When the system sees patterns that match those of known fraudsters it can flag that procurement as suspicious.
Text mining. Another popular advanced analytics tool, text mining identifies patterns in unstructured data, such as reports and social media. For example, if a procurement officer who makes $65,000 a year posts pictures of an extravagant purchase on social media, that may be of interest to investigators.
Advanced analytics allows for users to build models that identify attributes and patterns that are highly correlated with known fraud. Advanced analytics can look for deeper connections that ad-hoc methods miss. Does this look like the typical habit of bid riggers or those known for counterfeit parts? Does this series of invoices, stair-stepping up and down in dollar value, indicate a vendor trying to find the threshold of scrutiny?
These types of processes matter. Associative linking finds relationships among entities based on static attributes or transactional attributes that may seem innocuous at first, but even for valid transactions you want to be able to show you have done due diligence vetting relationships.
Both of these methods are good at detecting certain types of fraud. When used in combination with traditional tactics, they can present a bigger picture that can lead to more and more procurement fraud discovery. Fraud is not a victimless crime; government is trusted with public funds. Those funds fuel the government’s mission, but if even a small part is stolen by fraudsters, the public ultimately suffers.
Advanced analytics can serve as a way to reduce the amount of fraud impacting government funds. With advances in technology and established best practices, procurement fraud might one day be a thing of the past.
Ricky D. Sluder, certified fraud examiner, is a principal solution architect in the Security Intelligence Practice at SAS. He has 20 years of investigative experience in white collar crime, Medicare and Medicaid fraud, waste and abuse.